# lyramakesmusic/neuron-explorer

> A steering-first neuron explorer for Qwen3.5-4B: it pushes every MLP neuron up and down on prompts, keeps all rollouts, and lays the results out over a 3D view of the model for interpretability research.

- Magnitude: 5.2 out of 10 — Early signal
- Stars: 204 total · +73 stars measured 2026-10-25, 13:46–15:10 UTC, ≈ 106 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: Python · Created: 2026-10-21 · Last push: 2026-10-24
- GitHub: https://github.com/lyramakesmusic/neuron-explorer · Page: https://gitnova.dev/en/r/lyramakesmusic/neuron-explorer

## Useful for

- Run a steering sweep over all neurons of a layer and inspect the resulting rollouts
- Browse a 3D map of layers and neurons to find units with distinctive word clusters
- Chat with the model through the explorer's MCP server to steer neurons and read lenses live

## Why it’s here

- Star-counter measurements on 2026-10-25 (UTC), 13:46–15:10: 131 → 204 stars (+73). This is the change over that interval.
- Estimated end-of-day forecast: about +106 stars, using observed gains and the previous day.
- The repository is 4 days old and already has 204 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #107.
- About 27 forks a day — people are taking the code.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 19
- Issues and pull requests: 0
- Watchers: 0
- Average over the last week: 32 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 52

## Stars per day, last 5 days (oldest → newest, today is partial)

2026-10-21 … 2026-10-25: 0, 0, 0, 54, 73

## Spotted in now

- Top new repositories this week: #107

## More in this category

1. **deepseek-ai/DeepInfer** — 6.6 · Cooling · Language models · Python · +402 stars measured 2026-10-25, 00:09–15:10 UTC, ≈ 634 by evening
   Offline inference framework for running DeepSeek models at large scale: optimized kernels, MoE/Attention parallelism, deterministic sampling and structured outputs. Aimed at teams deploying DeepSeek-V4.1-Flash on NVIDIA SM100 or Huawei…
   Full card: https://gitnova.dev/en/r/deepseek-ai/DeepInfer.md
2. **routerhubSI/uncensored-ai-api** — 5.8 · Early signal · Language models · +193 stars measured 2026-10-25, 00:10–15:10 UTC, ≈ 294 by evening
   Gateway to AI APIs and models (Claude, GPT, Gemini, Grok, DeepSeek, GLM, Qwen) with one key, OpenAI- and Anthropic-compatible, offering uncensored and abliterated variants with pay-per-token billing.
   Full card: https://gitnova.dev/en/r/routerhubSI/uncensored-ai-api.md
3. **slee-persis/GVS5H** — 5.2 · Breakout · Language models · Python · +152 stars measured 2026-10-25, 04:56–15:10 UTC, ≈ 220 by evening
   A training-free method that runs five instances of one LLM in parallel, coordinating through a shared filesystem to solve hard coding problems, evaluated on LiveCodeBench.
   Full card: https://gitnova.dev/en/r/slee-persis/GVS5H.md
4. **Tencent/WeVisOne-VL** — 4.8 · Early signal · Language models · Jupyter Notebook · +74 stars measured 2026-10-25, 00:10–15:10 UTC, ≈ 108 by evening
   WeVisOne-VL is a vision-language model by the WeChat Vision Team at Tencent that unifies object-level and pixel-level perception: detection, referring localization, counting, pointing, OCR, segmentation, and alpha matting. It handles…
   Full card: https://gitnova.dev/en/r/Tencent/WeVisOne-VL.md
5. **Niko1221/Strata** — 4.7 · Steady · Language models · C++ · +523 stars measured 2026-10-25, 00:10–15:10 UTC, ≈ 828 by evening
   A C++ local inference engine that runs the 125B MoE model Qwen3.8-Flash-Next on a regular PC with one NVIDIA GPU (12-24 GB) and 64 GB RAM, exposing an OpenAI/Anthropic-compatible API on localhost.
   Full card: https://gitnova.dev/en/r/Niko1221/Strata.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-25 15:20 UTC, updated every 30 minutes.