© 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. 12107
    Prev
    Next
    INDEX
    Explanations

    which, if, when

    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
    Occ
    -0.08
     <=>
    -0.08
    è±ķ
    -0.08
    fm
    -0.07
    åŁºæľ¬
    -0.07
    ìĦł
    -0.07
    溢
    -0.07
    аÑĢа
    -0.07
    ä¸įå¿į
    -0.07
    ä¸Ģç³»åĪĹ
    -0.07
    POSITIVE LOGITS
    ç»IJ
    0.09
    год
    0.09
    æľī人说
    0.09
    ois
    0.08
    åĬ¡å®ŀ
    0.08
    ä¸įéĢļ
    0.08
    foon
    0.08
    å°½éĩı
    0.08
    ç»ĵåIJĪèµ·æĿ¥
    0.08
    èµ·çłģ
    0.08
    Activations Density 0.448%

    No Known Activations