© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21886
    Prev
    Next
    INDEX
    Explanations

    0.0

    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
    ×ķ×ij×Ķ
    -0.08
    é«ĺçŃīä¸ĵç§ijåŃ¦æł¡
    -0.07
    swire
    -0.07
     Ejem
    -0.07
    ysh
    -0.07
    chtest
    -0.07
    atina
    -0.07
    äºķ
    -0.07
    gages
    -0.07
     Geren
    -0.07
    POSITIVE LOGITS
    æĸĻçļĦ
    0.07
    ubl
    0.07
    æª
    0.06
    álló
    0.06
    ErrorException
    0.06
    æ¤
    0.06
    èı²å°Ķ
    0.06
    InputLabel
    0.06
    antum
    0.06
    outu
    0.06
    Activations Density 0.044%

    No Known Activations