Neuron Explorer: 3D visualization of per-layer Transformer neuron activations
arthurcolle · x · 2026-10-27
The author shares a screenshot of Neuron Explorer, an interpretability workbench that lays out Transformer layers as a 3D corridor. It supports feature search (e.g. "files"), per-layer neuron connection graphs, logit-lens views per layer, and a side panel showing live token/neuron activation details for the current chat. No accompanying text or project link is given in the post.
More from Research
- Model breeding begins: neuron combo makes Qwen believe it's Cookie Monster — yacineMTB · 2026-10-27
- EMNLP paper uses sparse autoencoders for text-based causal confounding adjustment — anjalie_f · 2026-10-27
- Volta releases Blackwell kernel verifier letting LLMs generate PTX directly, skipping compiler layers — Azaliamirh · 2026-10-27
- Johns Hopkins NLP Group Meets at EMNLP 2026 in Budapest — mdredze · 2026-10-27
- Poking a single neuron in Qwen turns it into an alien guiding civilization — MarcJSchmidt · 2026-10-27
- Looped transformer analysis pins down single neurons for non-duality, phonetics, and other concepts — burny_tech · 2026-10-27