© 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. 41303
    Prev
    Next
    INDEX
    Explanations

    letter codes and names

    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
    åı¯æ¯Ķ
    -0.07
    å¹´åħ¬åı¸
    -0.07
    orme
    -0.07
     composite
    -0.06
     dip
    -0.06
    QT
    -0.06
    éªĭ
    -0.06
    orm
    -0.06
    交æİ¥
    -0.06
    æºħ
    -0.06
    POSITIVE LOGITS
    æľŁéĻIJ为
    0.09
    /temp
    0.09
    -temp
    0.08
    æıIJè¦ģ
    0.08
    hdl
    0.08
    loon
    0.08
    æµĵåİļ
    0.08
    HandlerContext
    0.08
    Temp
    0.08
    å¤ĸéĿ¢çļĦ
    0.08
    Activations Density 0.004%

    No Known Activations