© 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. 43752
    Prev
    Next
    INDEX
    Explanations

    corrections and adjustments

    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
    ASSES
    -0.08
    enang
    -0.07
    asses
    -0.07
    AVED
    -0.07
    æĭħ
    -0.07
    atul
    -0.07
    yntax
    -0.07
    UTTON
    -0.07
    ilidad
    -0.07
    gency
    -0.07
    POSITIVE LOGITS
     corrections
    0.08
    误差
    0.08
    appa
    0.08
    ä½Ļ项
    0.08
    ä¿®
    0.07
    ç²¾ç»ĨåĮĸ
    0.07
     Corrections
    0.07
    reste
    0.07
     correction
    0.07
     finer
    0.07
    Activations Density 0.003%

    No Known Activations