© 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. 33509
    Prev
    Next
    INDEX
    Explanations

    first derivative of

    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
    çªģå¦Ĥåħ¶æĿ¥
    -0.11
     [âĢ¦]↵↵
    -0.10
    ä¸Ģæĸ¹éĿ¢æĺ¯
    -0.09
    èİ«åIJįåħ¶å¦Ļ
    -0.09
    ä¸ĭéĿ¢å°ıç¼ĸ
    -0.09
    ä»Ĭ天å°ıç¼ĸ
    -0.08
    ä¸ĢæŃ¥æŃ¥
    -0.08
    å¿ĥè¡Ģ
    -0.08
    ,âĢ¦↵↵
    -0.08
     inexp
    -0.08
    POSITIVE LOGITS
    ãģĿãĤĮãģ§ãĤĤ
    0.08
    exampleInput
    0.08
    unger
    0.07
    exampleInputEmail
    0.07
    iblings
    0.07
     Franz
    0.07
    æĪijçİ°åľ¨
    0.07
    .txt
    0.07
    ibling
    0.07
    .PNG
    0.07
    Activations Density 0.046%

    No Known Activations