© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 52171
    Prev
    Next
    INDEX
    Explanations

    code execution triggers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    cep
    -0.07
    åħ¨èĥľ
    -0.07
    çľ¼çľĭçĿĢ
    -0.06
    ç¥Ŀç¦ıä½ł
    -0.06
    çĦ¶åIJİ
    -0.06
    æĺ¯éĽĨ
    -0.06
    çĦ¶å¾Į
    -0.06
     Auton
    -0.06
    ts
    -0.06
    çĦ¶åIJİå°±
    -0.06
    POSITIVE LOGITS
    agate
    0.08
    memberOf
    0.08
    insky
    0.07
    SURE
    0.07
    è¿«åĪĩ
    0.07
    ylist
    0.07
    walt
    0.07
    gings
    0.07
    çIJ
    0.07
    æİ¢
    0.07
    Activations Density 0.004%

    No Known Activations