© 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. 55173
    Prev
    Next
    INDEX
    Explanations

    abbreviation, abbreviation, ticker, notation

    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
    Negative Logits
    endah
    -0.07
    ples
    -0.07
    üz
    -0.07
    itorial
    -0.07
    ÙĪغ
    -0.07
    丽çļĦ
    -0.07
     Anch
    -0.07
    幻影
    -0.07
    å½Ĵ宿
    -0.07
    æµģå¹´
    -0.07
    POSITIVE LOGITS
     обоз
    0.09
    符åı·
    0.09
     symbol
    0.08
    缩åĨĻ
    0.08
     prefix
    0.07
    prefix
    0.07
    åĨĻä½ľ
    0.07
    symbol
    0.07
     abbreviation
    0.07
     tắt
    0.07
    Activations Density 0.087%

    No Known Activations