© 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. 63961
    Prev
    Next
    INDEX
    Explanations

    names and birth years

    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
    è¿Ļå°±
    -0.13
    èĢĮåıĪ
    -0.10
    åľ¨å¤ĸ
    -0.10
    è¿ĻåĿĹ
    -0.09
    ä¸Ģæĸ¹éĿ¢
    -0.09
    æĬĬè¿ĻäºĽ
    -0.09
    è¿Ļæł·ä¸Ģ个
    -0.09
    人æ°ijæľįåĬ¡
    -0.09
     Zac
    -0.09
    èĢĮåİ»
    -0.08
    POSITIVE LOGITS
    rets
    0.09
    otope
    0.09
    fs
    0.08
    dit
    0.07
    .retry
    0.07
    -direct
    0.07
     etc
    0.07
    ÙħصÙĦ
    0.07
    (){}↵↵
    0.07
    çİ¢
    0.07
    Activations Density 0.351%

    No Known Activations