© 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. 992
    Prev
    Next
    INDEX
    Explanations

    normalization renormalization

    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
    èĤļåŃIJéĩĮ
    -0.08
    åľ°çIJĨ
    -0.07
     fare
    -0.07
     inland
    -0.07
    å°ıç±³
    -0.07
    बà¥į
    -0.06
    awali
    -0.06
    iterr
    -0.06
    大è¿IJ
    -0.06
    欺åĩĮ
    -0.06
    POSITIVE LOGITS
     ren
    0.09
     normalization
    0.08
    æİ¨è¿Ł
    0.08
    ren
    0.08
    ron
    0.07
    éĩįæķ´
    0.07
    urier
    0.07
    Normalization
    0.07
     dressing
    0.07
    sonian
    0.07
    Activations Density 0.001%

    No Known Activations