© 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. 37620
    Prev
    Next
    INDEX
    Explanations

    copyright and font

    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
    e
    -0.10
    o
    -0.10
    a
    -0.10
    àŃį
    -0.10
    ا
    -0.09
    asInstanceOf
    -0.09
    ÑģÑĮ
    -0.09
    oz
    -0.09
    ly
    -0.09
    aikan
    -0.09
    POSITIVE LOGITS
    翼翼
    0.11
    enticate
    0.10
    elled
    0.08
    lehem
    0.08
    enticated
    0.08
    è¿Ļæł·æĤ¨å°±åı¯ä»¥
    0.08
    ä½ľåĪĻ
    0.08
    éĺħè¯»æľ¬æĸĩåīį
    0.08
    缮çŀª
    0.08
    aurant
    0.07
    Activations Density 0.191%

    No Known Activations