© 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. 40072
    Prev
    Next
    INDEX
    Explanations

    digestive system and its functions

    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
    æĬĹéľĩ
    -0.09
    èĢģå¹´
    -0.09
    ness
    -0.09
    à¸ļาà¸Ĺ
    -0.08
    形象
    -0.08
    æľīè¿ĩ
    -0.08
    åħ¬æĬ¥
    -0.08
    åĹª
    -0.08
    ispers
    -0.08
    èµĦè´¨
    -0.08
    POSITIVE LOGITS
    utable
    0.10
    æĸ¹éĿ¢
    0.09
    ä¸į好
    0.09
    fid
    0.09
     system
    0.09
    æĸ¹éĿ¢çļĦ
    0.09
    аÑĨион
    0.09
    utors
    0.09
    ä¸Ĭãģ®
    0.08
     tract
    0.08
    Activations Density 0.037%

    No Known Activations