© 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. 34712
    Prev
    Next
    INDEX
    Explanations

    unpublished, uncollected, unidentified

    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
    urr
    -0.08
    æĤ¨æīĢåľ¨çļĦä½įç½®
    -0.08
    ställ
    -0.08
    urras
    -0.08
    tright
    -0.08
    audi
    -0.08
    #undef
    -0.08
    äär
    -0.08
    insip
    -0.08
    elv
    -0.08
    POSITIVE LOGITS
    æĪĸæľª
    0.13
    æĪĸå°ij
    0.09
    æĪĸ被
    0.08
    /un
    0.08
    å¤ļå¹´çļĦ
    0.07
    æĪĸ缺
    0.07
    æĪĸä¸į
    0.07
     Roh
    0.06
    ä¹Łæľª
    0.06
    erved
    0.06
    Activations Density 0.134%

    No Known Activations