© 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. 47767
    Prev
    Next
    INDEX
    Explanations

    re- prefix

    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
    èĩªèº«çļĦ
    -0.10
    ä½ľä¸ºä¸Ģ个
    -0.10
    zym
    -0.10
    尽头
    -0.10
    æĶ¹åıĺäºĨ
    -0.10
    竺
    -0.10
    ingles
    -0.10
    âļ½
    -0.10
    æĦļ
    -0.09
    åģľä¸ĭæĿ¥
    -0.09
    POSITIVE LOGITS
     Gore
    0.08
    able
    0.08
    uell
    0.08
    phrase
    0.07
    ees
    0.07
    wards
    0.07
    /re
    0.07
    è·Łè¿Ľ
    0.07
    ç»Ń
    0.07
    é¢ijé¢ij
    0.07
    Activations Density 0.117%

    No Known Activations