© 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. 23775
    Prev
    Next
    INDEX
    Explanations

    ".xls" or file extensions

    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
     dot
    -0.06
     Laure
    -0.06
    pl
    -0.06
    åĴĮç»Ħç»ĩ
    -0.06
    Lik
    -0.06
    minus
    -0.06
    olon
    -0.06
    ais
    -0.06
    dot
    -0.06
    im
    -0.05
    POSITIVE LOGITS
    attery
    0.08
    .xls
    0.08
    èĨĽ
    0.08
     FormData
    0.08
    attering
    0.07
    ×ķ×IJ
    0.07
    iris
    0.07
    attended
    0.07
    æĢĿæĥ³å·¥ä½ľ
    0.07
    ä½łæĺ¯æĪij
    0.07
    Activations Density 0.002%

    No Known Activations