© 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. 60802
    Prev
    Next
    INDEX
    Explanations

    years and numbers

    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
     spirited
    -0.07
     sty
    -0.07
    oux
    -0.07
    _dependencies
    -0.07
    èĦ
    -0.07
    otted
    -0.06
    íĭ´
    -0.06
    olim
    -0.06
     gifs
    -0.06
    onom
    -0.06
    POSITIVE LOGITS
    纪
    0.07
    ç§ijåѦä¸İæĬĢæľ¯
    0.07
     menda
    0.07
    ippo
    0.07
    稽
    0.07
    _equals
    0.07
    ä»ĬæľĿ
    0.07
    è§ģåºķ
    0.07
    åºĶäºĪ
    0.07
    åIJĮ声
    0.06
    Activations Density 0.031%

    No Known Activations