© 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. 51939
    Prev
    Next
    INDEX
    Explanations

    title:

    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
    afs
    -0.07
    ä¸Ŀè·¯
    -0.07
    uvia
    -0.07
    éªĮ
    -0.07
    éĻ¤
    -0.06
    è°ĭ
    -0.06
    pas
    -0.06
    ERS
    -0.06
    ä¹ĺ
    -0.06
    avana
    -0.06
    POSITIVE LOGITS
    ÃĬN
    0.08
    лиÑģÑĤи
    0.08
    æĦıæĥ³
    0.07
    ÑĥÑĢо
    0.07
    å¦ĤæѤä¸ĢæĿ¥
    0.07
    羣æŃ£åľ°
    0.07
    ä½ķä¸į
    0.07
    ä»İèĢĮ导èĩ´
    0.07
    .undefined
    0.07
    etes
    0.07
    Activations Density 0.009%

    No Known Activations