PLTs for mechanistic interpretability research. Compatible with circuit-tracer for generating attribution graphs and analyzing model circuits.
Mateusz
mntss
AI & ML interests
None yet
Recent Activity
new activity 17 days ago
neuronpedia/jacobian-lens:Add Qwen3.5-4B and Qwen3.6-27B Jacobian lenses (n_prompts=1000) updated a model 18 days ago
neuronpedia/jacobian-lens updated a model 10 months ago
mntss/cltOrganizations
