© 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. 891
    Prev
    Next
    INDEX
    Explanations

    you'll

    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
    Not in Any Lists

    No Comments

    Negative Logits
     perhaps
    -0.07
     (
    -0.06
    ↵
    -0.06
    bacher
    -0.06
    èªĩ
    -0.06
     D
    -0.06
    è±¹
    -0.06
     preferred
    -0.06
     P
    -0.06
     maybe
    -0.06
    POSITIVE LOGITS
    æīĢæĢĿ
    0.09
     lawy
    0.09
    allee
    0.08
    æĥħåĨµè¿Ľè¡ĮäºĨ
    0.08
     exéc
    0.08
    tested
    0.08
    |[
    0.08
    teh
    0.08
    alley
    0.08
    pei
    0.08
    Activations Density 0.007%

    No Known Activations