AI & ML interests

Interpretability for open models. We read models from the inside, neuron by neuron. Then we make them better.

Recent Activity

INTERPRETIC  updated a collection about 19 hours ago
Qwen3.8-27B Uncensored v3
INTERPRETIC  updated a collection about 19 hours ago
Qwen3.8-27B Uncensored v3
View all activity

INTERPRETIC 
updated a Space 4 days ago
INTERPRETIC 
published a Space 4 days ago