© 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. 40125
    Prev
    Next
    INDEX
    Explanations

    football clubs

    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
    å®īå®ģ
    -0.10
    缯
    -0.09
    طر
    -0.09
    ç²¢
    -0.09
    éĿŀåĩ¡
    -0.09
    æĹłå¿§
    -0.09
    éĻIJæŶ
    -0.09
     пÑĢоб
    -0.09
    å²ĺ
    -0.09
    åĪĿå¿ĥ
    -0.08
    POSITIVE LOGITS
    ä¼łåªĴ
    0.10
    æ¶İ
    0.10
    ities
    0.08
    è°Ĭ
    0.08
    HAM
    0.08
     Nh
    0.08
    osto
    0.08
    祢
    0.08
    æİĮæı¡äºĨ
    0.08
     Hol
    0.08
    Activations Density 0.001%

    No Known Activations