© 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. 60923
    Prev
    Next
    INDEX
    Explanations

    pad followed by different suffixes

    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
    涯
    -0.11
    erk
    -0.11
    à¹Į
    -0.10
    è¯ŀ
    -0.10
    AIN
    -0.09
    ç½ijé¦ĸ页
    -0.09
    ksen
    -0.09
    ç²²
    -0.09
    naire
    -0.09
    alse
    -0.08
    POSITIVE LOGITS
    TURE
    0.12
    æ±Łåİ¿
    0.12
    åŃIJéĩĮ
    0.11
    tribute
    0.10
    flix
    0.10
    èĩ¾
    0.09
    rone
    0.09
    rão
    0.09
    folios
    0.09
    Sci
    0.09
    Activations Density 0.017%

    No Known Activations