lyramakesmusic/neuron-explorer
App
Can I trust it?
Be careful with this one.
Warnings Check
Very new: it was created 5 days ago. Wait a little before installing it.
Stars from real accounts No data
We haven't checked its stars for fakes yet.
Active OK
Last change yesterday.
Licence Careful
No licence: legally you can't reuse the code, unless the README says otherwise.
Quick checks from public data. They help, but they are no guarantee.
What it is
A steering-first explorer for Qwen3.5-4B that pushes every MLP neuron in a layer up and down on a few prompts, keeps all rollouts, and lays the results out in a 3D view of the model. It also runs a live steered chat, logit and steer lenses, and inference over user text.
Who it's for
Researchers and developers doing mechanistic interpretability on Qwen3.5-4B who want to browse neuron steering results
How to use it
Install
uv syncFrom its README. Check it there before running it.
Ready-made installers, when the project publishes them, are on its latest release.
Ask your AI to set it up
Paste this into Claude, ChatGPT or your coding assistant.
Help me install and set up lyramakesmusic/neuron-explorer in my project. Follow its README: https://github.com/lyramakesmusic/neuron-explorer. Explain each step and check it is safe before running anything.
Star curve
On the radar
Its place among the radar's top 100, day by day, with #1 at the top. Gaps are days it was out of the top 100.
Records
- Best place on RepoAlerts: #8, on 26 Oct 2026
Get alerts for repos like this
We'll email you when something in Models & inference starts rising. Free, once a week, only what matches.
20,244 GitHub repos watched and ranked every hour. Figures as of 26 October 2026.
What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy
For maintainers
Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.
[](https://repoalerts.com/repo/lyramakesmusic/neuron-explorer?ref=badge)Similar repos
- kaichen-z/SteerAct
Research code for steering frozen robot action models (pi0.5 and Fast-WAM) on RoboTwin 2.0 tasks. Uses a pretrained sparse autoencoder to rank features from successful and failed rollouts, monitor exe
- google-research/harness2
A Python framework for recursive agent harnessing, which refines the prompts, tools, memory, skills and orchestration around a fixed model. It runs a propose-probe-compose loop per task and keeps a pe
- nace-ai/kapitsa
Inference engine for Apple silicon Macs that runs Qwen and Nemotron models locally. It can start coding agents such as opencode, Claude Code, Codex or pi on a local model and serves OpenAI and Anthrop
- THUSI-Lab/GameScaling
Inference client and system-prompt template for GameScaling, a set of Qwen3.5 vision-language models with continued pre-training on keyboard-and-mouse gameplay. Given the current frame and recent hist
- plotarmordev/drama-tensorfold
Recipe that builds the TensorFold native Zig/CUDA engine with opt-in patches to run Fish Audio's Drama 3 text-to-speech on an NVIDIA GB10. It starts a local server with an OpenAI-style /v1/audio/speec
- pzs19/HarnessPro
A framework that recursively improves the harness of an AI agent (its instructions, tools and runtime policies) by diagnosing execution traces and selecting candidate changes with synthesized tests. O