© 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. 16916
    Prev
    Next
    INDEX
    Explanations

    advances in research and knowledge

    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
    åľ¨æľªæĿ¥
    -0.10
    зам
    -0.09
     Ñģобой
    -0.09
     Herrera
    -0.08
    ç½®äºİ
    -0.08
    à¹Ĥà¸ŀ
    -0.08
    .assertIsNot
    -0.08
    OLON
    -0.08
    åįŀ
    -0.08
    ä¸įå¾Ĺ
    -0.08
    POSITIVE LOGITS
    æĸ¹éĿ¢çļĦ
    0.10
    è¿Ļ件äºĭæĥħ
    0.10
     behalf
    0.09
    ä¸Ģæĸ¹éĿ¢æĺ¯
    0.09
    ç£ķ
    0.09
    çıĬçijļ
    0.09
    çī¹åĪ«æĺ¯åľ¨
    0.09
    åŃIJå¼Ł
    0.09
    æĸ¹éĿ¢
    0.09
    åIJĦ个æĸ¹éĿ¢
    0.09
    Activations Density 0.383%

    No Known Activations