© 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. 26147
    Prev
    Next
    INDEX
    Explanations

    never such a

    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
    ä¸įåı¯éģ¿åħį
    -0.10
    åĭ¿
    -0.09
    èĢĮä¸įæĺ¯
    -0.09
    ãģªãĤīãģªãģĦ
    -0.09
    è¢Ń
    -0.09
    è¯ķè¯ķ
    -0.08
    arend
    -0.08
    带é¢Ĩ
    -0.08
    ritz
    -0.08
     кÑĢÑĭ
    -0.08
    POSITIVE LOGITS
    å¦ĤæѤ
    0.11
    è¿Ļä¹Īå¤ļ
    0.10
     EVER
    0.10
    atis
    0.10
    ç«Łæĺ¯
    0.10
    åĨħå¤ĸ
    0.09
    æijĩ
    0.09
    ç«ŁçĦ¶
    0.09
    çŁŃçŁŃ
    0.09
    ä¸Ģ个èģĮä¸ļ
    0.09
    Activations Density 0.046%

    No Known Activations