© 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. 63788
    Prev
    Next
    INDEX
    Explanations

    Ridge Public

    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
    æłİ
    -0.09
     Gang
    -0.09
    ä¸Ńç¾İ
    -0.09
    er
    -0.09
    exas
    -0.08
    ement
    -0.08
     Fen
    -0.08
    èĬĿåĬłåĵ¥
    -0.08
     GANG
    -0.08
     nex
    -0.08
    POSITIVE LOGITS
    æ³
    0.11
    íļĮìĤ¬
    0.10
    å¿ħä¸įåı¯
    0.09
    æĬ¥ç¤¾
    0.09
    æľīè¿Ļæł·çļĦ
    0.09
    åij½åIJį为
    0.09
    说çĿĢ
    0.09
    è¯Ħå®ļ
    0.09
    ä»ĸ说
    0.09
     Pins
    0.09
    Activations Density 0.001%

    No Known Activations