© 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. 59925
    Prev
    Next
    INDEX
    Explanations

    cross-sectional study

    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
    -tracking
    -0.09
    ç¼Ī
    -0.09
     Melo
    -0.08
    æµģæ°´
    -0.07
     tracking
    -0.07
    <num
    -0.07
    TRACK
    -0.07
    tracking
    -0.07
     track
    -0.07
     Tracking
    -0.07
    POSITIVE LOGITS
    éĿĻæĢģ
    0.16
     static
    0.13
     statically
    0.12
     stationary
    0.12
    static
    0.12
    Static
    0.12
     Static
    0.12
    -static
    0.11
    éĿĻæŃ¢
    0.11
    /static
    0.11
    Activations Density 0.404%

    No Known Activations