© 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. 14489
    Prev
    Next
    INDEX
    Explanations

    for all

    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
    owski
    -0.09
    éĢ¢
    -0.08
    ovski
    -0.08
     "[%
    -0.07
    ë¡ľìĿĺ
    -0.07
    ihu
    -0.07
    ะ
    -0.07
    es
    -0.07
    对äºİ
    -0.07
    uru
    -0.07
    POSITIVE LOGITS
    iable
    0.08
    unately
    0.08
    ÃįN
    0.07
    æĹ¥åŃIJéĩĮ
    0.07
    ially
    0.07
    ä»ĸ们æĺ¯
    0.07
    emment
    0.07
    езде
    0.07
    itorio
    0.07
     Zwecke
    0.07
    Activations Density 0.026%

    No Known Activations