© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 18915
    Prev
    Next
    INDEX
    Explanations

    excellent and lacks meaningful

    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
    Not in Any Lists

    No Comments

    Negative Logits
    åĽłä¸ºå¥¹
    -0.10
    ãģ§ãģĹãĤĩãģĨãģŃ
    -0.09
    å¹Į
    -0.09
    éĻIJå®ļ
    -0.08
    ç¼Ļ
    -0.08
    oyo
    -0.08
    Subtitle
    -0.08
    UPI
    -0.08
    ä»ĸèĩªå·±
    -0.08
    olv
    -0.08
    POSITIVE LOGITS
    èµŀèµı
    0.11
    çľĭä¸įåĩº
    0.09
    æĸ°é¢ĸ
    0.09
    èµŀæĪIJ
    0.09
    åĿ¨
    0.09
    è´
    0.08
    æĤ¨çļĦ
    0.08
    å·²ç»ıè¾¾åĪ°
    0.08
    æ¶ķ
    0.08
     Excellent
    0.08
    Activations Density 0.089%

    No Known Activations