Model
Qwen 32B
A 32-billion-parameter large language model in Alibaba's Tongyi Qianwen (Qwen) series.
Timeline (last 90 days)
Oct 17
A preliminary audit on the Qwen 32B model shows that about 90% of neurons have only one main meaning, about 7% have two related secondary meanings, and only 2-4% are uninterpreted.
Unverified50%