Neuron Explorer for Qwen3.5-4B: See every neuron at work, make targeted edits A steering-first Neuron Explorer for Qwen3.5-4B was released, pushing every MLP neuron in a layer up and down across a few prompts, keeping every rollout, and laying the results over a 3D view of the model. The explorer loads Qwen3.5-4B locally on MPS, CUDA or CPU for live steered chat, lens, connections and inference, and its Claude tab runs the claude CLI with the explorer as an MCP server (explorer/agent_mcp.py) that can read neurons, cones and lenses, run the live model, and move the map and highlights. The sweep pipeline runs on a CUDA 13 GPU pod with the steering fork of vLLM (RhizoNymph/vllm), using main_rel doses as 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. 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. uv sync uv run python explorer/server.py http://localhost:8791 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. - map : the model's layers in perspective, attention and MLP per layer, one point per neuron. Hover shows a neuron's steer lens and logit lens; click opens it; click a layer's label to view its sheet face-on. writes places neurons with similar down-projection columns next to each other. - list : units ranked by word-cluster mass against random-direction controls; lens searches the steer and logit lenses for a token, fires runs your text through the model and filters neurons by activation. - neuron : steered rollouts per prompt and dose, a three-column multi-turn steered chat −, 0, + , lens and connections, and a name. - embeddings : UMAP of a layer's rollouts, coloured by neuron, prompt, dose or kind. - Claude fourth neuron-panel tab, or the right-edge handle : a chat running the claude CLI installed and logged in with the explorer as an MCP server explorer/agent mcp.py . It reads neurons, cones and lenses, runs the live model steering, activations, next-token logprobs, ablations , moves the map, list and highlights, and has file tools and a shell in your home folder. Its prompt is explorer/agent prompt.md plus explorer/agent methodology.md , and explorer/agent prompt.local.md when present untracked, for your own additions ; EXPLORER CLAUDE MODEL picks the model. The server answers only pages and tools on this machine. Runs on a CUDA 13 GPU pod with the steering fork of vLLM RhizoNymph/vllm https://github.com/RhizoNymph/vllm . bash sweep/setup pod.sh fork, deps, model; writes /workspace/env.sh python sweep/neuron stats.py --layers 22 --tokens 2000000 --out stats/q35-4b python sweep/steer sweep.py --stats stats/q35-4b L22.npz --design main rel --dose-unit rel \ --neurons all --random-controls 256 --run q35-4b-L22 sweep/run depth.sh "4 9 13 17" 384 64 random-subset sweep across several layers 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. | script | output | |---|---| | sweep/neuron stats.py | per-neuron activation extremes by sign regime, down columns, residual norms | | sweep/steer sweep.py | runs/