© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 26146
    Prev
    Next
    INDEX
    Explanations

    school curriculum and lessons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    人为
    -0.09
    æĹłçŁ¥
    -0.09
    _CLI
    -0.09
    è·ŁæĪij
    -0.09
    åİĤ
    -0.09
    èĩªè§ī
    -0.08
     Posting
    -0.08
    CharArray
    -0.08
    çģ¼
    -0.08
     Gio
    -0.08
    POSITIVE LOGITS
    课åłĤæķĻåѦ
    0.10
    ä¸ĢéŨ
    0.10
    ç¿¡
    0.09
    大纲
    0.09
    ongo
    0.09
    æķĻæĿIJ
    0.09
    (Unit
    0.09
    æ·±åħ¥å¼Ģå±ķ
    0.09
    å¾ĭ
    0.09
    å·¥ä½ľå®¤
    0.09
    Activations Density 0.082%

    No Known Activations