© 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. 27787
    Prev
    Next
    INDEX
    Explanations

    code syntax elements

    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
    åĪĨåĮº
    -0.07
    trom
    -0.07
    ãĤ¤ãĥ¤
    -0.07
    .tar
    -0.07
    èī²å·®
    -0.07
    æĮ¯
    -0.07
    é¨
    -0.07
    dataArray
    -0.07
    头çĹĽ
    -0.07
    gau
    -0.07
    POSITIVE LOGITS
     synt
    0.08
    ouser
    0.07
    è¯į
    0.07
    çļĦè¯į
    0.07
     node
    0.07
     punctuation
    0.07
     Täter
    0.07
    umin
    0.07
     expression
    0.07
    builtin
    0.06
    Activations Density 0.093%

    No Known Activations