© 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. 16570
    Prev
    Next
    INDEX
    Explanations

    sports teams

    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¸ĢåIJį
    -0.11
    ç¼Ĵ
    -0.10
    çļĦä¸Ģ大
    -0.09
    è¿ĻåIJį
    -0.09
    çĶļèĩ³è¿ĺ
    -0.09
    ä¸Ģå¾ĭ
    -0.09
    ächt
    -0.09
    ÑģÑĤвÑĥ
    -0.09
    æĪIJ为ä¸ĢåIJį
    -0.08
    ä¸Ģ人
    -0.08
    POSITIVE LOGITS
    _HC
    0.09
     رب
    0.08
     hur
    0.08
    åĩĿèģļåĬĽ
    0.08
     rab
    0.08
     Ferguson
    0.08
    ଡ
    0.08
    argin
    0.08
    вÑıз
    0.08
    .bo
    0.08
    Activations Density 0.033%

    No Known Activations