© 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. 26104
    Prev
    Next
    INDEX
    Explanations

    lens, eyes, perspective

    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
    imators
    -0.09
    bsolute
    -0.09
    inux
    -0.09
    atus
    -0.09
    achi
    -0.09
    ä¾ĭè¡Į
    -0.08
    æŃ¥ä¼IJ
    -0.08
    大éĿ¢ç§¯
    -0.08
    ĵåIJį
    -0.08
    opause
    -0.08
    POSITIVE LOGITS
     lens
    0.13
    éķľå¤´
    0.11
     Rect
    0.10
    çľĭå¾ħ
    0.09
    è¿Ļç§įæĸ¹å¼ı
    0.09
    æĸ°éĹ»è®°èĢħ
    0.09
    ä¸¥æł¼æī§è¡Į
    0.09
    éķĴ
    0.09
     lenses
    0.09
    jur
    0.09
    Activations Density 0.023%

    No Known Activations