© 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. 969
    Prev
    Next
    INDEX
    Explanations

    YA, children, books, fiction, literature

    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
     Diet
    -0.09
    éģĴ
    -0.09
    é£İæ³¢
    -0.08
    гиб
    -0.08
    åĻİ
    -0.08
    æĹģ
    -0.08
    rum
    -0.08
    èµĭ
    -0.08
    æĸ¡
    -0.08
    æįº
    -0.08
    POSITIVE LOGITS
    èĥ¸éĥ¨
    0.10
    çķĮçļĦ
    0.09
    uset
    0.09
    ÑİÑīÑĥÑİ
    0.09
    æĬĬ她
    0.08
    åIJijãģij
    0.08
     Chest
    0.08
    itives
    0.08
    sic
    0.08
    ish
    0.08
    Activations Density 0.024%

    No Known Activations