Steering-first neuron explorer for Qwen3.5-4B: push every MLP neuron, keep every rollout, browse the results
☆1,996Nov 2, 2026Updated 2 weeks ago
Alternatives and similar repositories for neuron-explorer
Users that are interested in neuron-explorer are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Character Creation Through Strategic Ablation — Permanently ablating personality steering vectors into LLM weights using contrastive acti…☆46Nov 6, 2026Updated last week
- A catalog of every MLP neuron and attention head of Qwen3-8B and Gemma 4 12B, read from the weights through two Jacobian lenses (R and S)…☆53Updated this week
- Find, rank and steer MLP neurons of GGUF models on llama.cpp; export control vectors; 3D web UI and MCP server☆104Updated this week
- web app for chatting with llms on openrouter with leaked unabridged reasoning☆108Oct 24, 2026Updated 3 weeks ago
- NEURALESE — 3D in-browser weight hacking of TinyStories-8M. Edit a tiny LM's weights live and watch it go weird.☆27Nov 5, 2026Updated last week
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- A vLLM fork that adds support for steering, an activation capture consumer plugin system, dynamic activation-conditioned steering, and ac…☆28Nov 3, 2026Updated 2 weeks ago
- Turn your regular JavaScript code into a neural net.☆2,160Updated this week
- Refusal removal as a loadable KV-cache graft — zero weight modification, no refusal-direction projection, fully reversible.☆275Sep 21, 2026Updated last month
- Companion code for the global workspace interpretability paper☆2,182Oct 10, 2026Updated last month
- ☆25Updated this week
- Official Project Page for Recurrent Looped Transformer (RLT) (https://arxiv.org/abs/2610.07591)☆1,146Nov 5, 2026Updated last week
- ☆13Updated this week
- Modulo lets agents running local models try modifying their own activations to change their inner state. Changes decay after a certain ti…☆41Updated this week
- Agent Skill for fine-tuning an agentic model on your own Claude Code sessions with Tinker. Works in Claude Code, Codex and OpenCode.☆325Nov 7, 2026Updated last week
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Experiments on whether language models can learn to detect read-only activation probes☆70Oct 26, 2026Updated 3 weeks ago
- Plug-and-play PyTorch transformer research framework. Swap attention, FFN, norm, positional, connection, projection, optimizer, scheduler…☆18Oct 25, 2026Updated 3 weeks ago
- An LLM running on an NPU inside an LLM. Karpathy's stories260K writing stories on a vector unit compiled into Qwen3.5-4B's weights.☆139Nov 5, 2026Updated last week
- Headless 3D and VFX engine for agents. Research preview.☆1,617Updated this week
- Qwen3.5-2B with a SIMT GPU inside its weights, 45 compiled layers in front of Qwen’s own, using its Gated DeltaNet layers as registers an…☆121Nov 1, 2026Updated 2 weeks ago
- ☆98Nov 7, 2026Updated last week
- a systemone proxy using embeddings that distills a teacher model☆516Nov 9, 2026Updated last week
- Your GeForce runs AI at half speed. This fixes it for 20/30/40 series cards. Up to 2× FP16 / BF16 / TF32 tensor throughput☆20,169Updated this week
- ☆57Oct 20, 2026Updated 3 weeks ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- DeepInfer: High-performance, large-scale inference framework for DeepSeek models☆26,157Nov 3, 2026Updated 2 weeks ago
- A toolkit for Weight-Space Programming / Reading☆41Updated this week
- Speedrun for pretraining without backpropagation☆451Nov 5, 2026Updated last week
- A framework for building decision-model harnesses for any kind of task. Your program offers the model a short list of next steps, and the…☆446Oct 30, 2026Updated 2 weeks ago
- ☆678Nov 1, 2026Updated 2 weeks ago
- A brain that learns from live experience. System 1 by default: perception, memory, plasticity and action. Optional System 2 for self-obse…☆636Updated this week
- ☆29Oct 18, 2026Updated 3 weeks ago
- Self-hosted metasearch and grounding engine for AI agents, based on SearXNG. Rust, JSON API, optional page text.☆981Updated this week
- ☆43Nov 11, 2026Updated last week
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- Local autoresearch on a MacBook, with Flint: geometry, scheduling and machine learning experiments.☆111Oct 27, 2026Updated 3 weeks ago
- RSI-Anything: Unlocking Recursive Self-Improvement with World Models☆1,172Oct 13, 2026Updated last month
- Official Project Page for KL-Regularized Policy Optimization (KLPO) (https://arxiv.org/abs/2610.08963)☆193Nov 5, 2026Updated last week
- Accelerate high-latency GEO inflight Wi-Fi via warm BBR TCP multiplexing + 1-RTT Ground-TLS + zlib (zero dependencies)☆1,099Nov 7, 2026Updated last week
- neuron-lens.com: what each neuron and attention head inside Qwen3-8B and Gemma 4 12B responds to, and what it makes the model say☆23Updated this week
- A self-improving RLM agent for coding workflows and long-running autonomous tasks.☆22,799Updated this week
- Build RL environments for any domain from real cases that Browser Use agents mine from the web☆169Oct 21, 2026Updated 3 weeks ago
Are these results useful?