© 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. 60875
    Prev
    Next
    INDEX
    Explanations

    legal citations

    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
    姨
    -0.12
    AUSE
    -0.10
    婵
    -0.09
    thon
    -0.09
    uset
    -0.09
    å½¼
    -0.09
    ç§įç§į
    -0.09
    é¹Ĺ
    -0.09
    åĿĢ
    -0.09
    æĹ¥æĬ¥ç¤¾
    -0.09
    POSITIVE LOGITS
    cmc
    0.10
    etails
    0.10
    é»ijé¾Ļ
    0.08
    decorators
    0.08
    gram
    0.08
    kaar
    0.08
    degree
    0.08
    cheon
    0.08
     lighten
    0.08
     Finch
    0.08
    Activations Density 0.230%

    No Known Activations