© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 41968
    Prev
    Next
    INDEX
    Explanations

    preschool context

    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
     youthful
    -0.08
    é«ĺä¸Ń
    -0.07
    éĿĴ年人
    -0.07
    åŃIJå¼Ł
    -0.07
     ì²ŃìĨĮëħĦ
    -0.07
     Razor
    -0.07
    èĢģèĢģå®ŀ
    -0.06
     Adolescent
    -0.06
     maggi
    -0.06
     Youth
    -0.06
    POSITIVE LOGITS
    ä¿ĿæķĻ
    0.12
    æĹ©æķĻ
    0.11
    让幼åĦ¿
    0.11
    ä¿ĿèĤ²
    0.11
    åħ¥åĽŃ
    0.10
    æĪijåĽŃ
    0.10
     preschool
    0.10
    å¹¼åĦ¿åľ¨
    0.10
    ä¸ŃçıŃ
    0.09
    åĽŃéķ¿
    0.09
    Activations Density 0.053%

    No Known Activations