lyramakesmusic/neuron-explorer: Steering-first neuron explorer for Qwen3.5-4B: push every MLP neuron, keep every rollout, browse the results ·
Steering-first neuron explorer for Qwen3.5-4B: push every MLP neuron, keep every rollout, browse the results Steering-first neuron explorer for Qwen3.5-4B. Every MLP neuron in a layer is pushed up and down on a few prompts, every rollout is kept, and the explorer lays the results out over a 3D view of the model. Reads sweep runs from runs/ and per-layer stats from stats/, both produced by the sweep below; the caches in explorer/cache/ ship with the repo. Loads Qwen3.5-4B locally (MPS, CUDA or CPU) for live steered chat, lens, connections and live inference over your own text. Runs on a CUDA 13 GPU pod with the steering fork of vLLM (RhizoNymph/vllm). main_rel doses are fractions of the median residual norm leaving the layer: {who, snake, orange} × {−0.7, +0.5, +0.8} and {free} × {+3}, plus one unsteered baseline per prompt. research_log.md holds the findings and reasoning; NOTES.md the source notes. Steering-first neuron explorer for Qwen3.5-4B: push every MLP neuron, keep every rollou