© 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. 1171
    Prev
    Next
    INDEX
    Explanations

    each followed by word parts

    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
    impl
    -0.06
    大æľī
    -0.06
    åħ¨
    -0.06
    estr
    -0.06
    ellig
    -0.06
     yap
    -0.06
    /fast
    -0.06
    ä¸įåĪĨ
    -0.06
    éĵŃ
    -0.06
     piece
    -0.06
    POSITIVE LOGITS
    ilies
    0.08
    ÑĤоÑĢи
    0.08
    lte
    0.08
    elte
    0.08
    hte
    0.08
    ï¼įï¼įï¼įï¼į
    0.08
    ---</
    0.08
    etine
    0.07
    èĢĮåIJĮ
    0.07
    _MSB
    0.07
    Activations Density 0.037%

    No Known Activations