© 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. 34706
    Prev
    Next
    INDEX
    Explanations

    impurities

    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
    efined
    -0.10
    è¡ĵ
    -0.09
    ç»İ
    -0.09
    epend
    -0.08
    å°Ķ
    -0.08
    å«Ĥ
    -0.08
    ÙĦسة
    -0.08
    aming
    -0.08
    owed
    -0.07
    sav
    -0.07
    POSITIVE LOGITS
    纷åijĪ
    0.08
    पà¥Ĥरà¥įण
    0.07
    unction
    0.07
    åĴĮä¸įèī¯
    0.07
    ieux
    0.07
    perse
    0.07
    zyb
    0.07
    zyn
    0.07
    -free
    0.06
    ouston
    0.06
    Activations Density 0.009%

    No Known Activations