© 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. 7227
    Prev
    Next
    INDEX
    Explanations

    code with methods and definitions

    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
    vel
    -0.07
     Num
    -0.06
    mer
    -0.06
    )y
    -0.06
    ì¡´
    -0.06
     ;-
    -0.06
     Bany
    -0.06
    beth
    -0.06
    Å¡n
    -0.06
    -0.06
    POSITIVE LOGITS
    交æµģåŃ¦ä¹ł
    0.08
    ÙĤت
    0.07
    书å±ĭ
    0.07
    _TRANSFER
    0.07
    ensión
    0.07
    ezi
    0.07
    _SETUP
    0.07
    æ¡¥åĮº
    0.07
    æĸĩåĮĸ交æµģ
    0.06
    ТУ
    0.06
    Activations Density 0.001%

    No Known Activations