Lead story
Models & availability
Latest
Lead story
Models & availability
Latest
Alibaba introduces Qwen-Scope, an interpretability toolkit that uses Sparse Autoencoders (SAEs) trained on Qwen3 and Qwen3.5 series models to decompose hidden representations into interpretable features, enabling controllable inference, data classification and synthesis, targeted fine-tuning, and evaluation redundancy analysis.
From the source
Today, we are excited to introduce Qwen-Scope, an interpretability toolkit trained on the Qwen3 and Qwen3.5 series models.
qwen.ai