© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 56201
    Prev
    Next
    INDEX
    Explanations

    announcements and future plans

    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
    ä½İ头
    -0.09
     reportedly
    -0.09
    æĪĸèĢħåħ¶ä»ĸ
    -0.08
    çİ°å¦Ĥä»Ĭ
    -0.08
    bah
    -0.08
     LS
    -0.08
    .subtract
    -0.08
    åįĥå¹´
    -0.08
    rie
    -0.08
    weis
    -0.08
    POSITIVE LOGITS
    请大家
    0.13
    为大家
    0.12
     exciting
    0.11
    ç»Ļ大家
    0.10
    鹦
    0.09
    å¸ĮæľĽå¤§å®¶
    0.09
    è¿Ļæĺ¯æĪij们
    0.09
    éĢĤ度
    0.09
    好æ¶Īæģ¯
    0.09
    æĸ°çļĦä¸Ģ
    0.09
    Activations Density 0.074%

    No Known Activations