© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62877
    Prev
    Next
    INDEX
    Explanations

    bib, JR, ID, 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
    Ĭ
    -0.07
    {}
    -0.07
    éĩįä»»
    -0.07
    æĸ°åĬłåĿ¡
    -0.07
    ä¸įå®ī
    -0.06
    æĢ¥
    -0.06
    ราà¸ļ
    -0.06
    èħ°
    -0.06
    maal
    -0.06
    .getBytes
    -0.06
    POSITIVE LOGITS
    lette
    0.07
    åIJįæĢĿ
    0.07
     пÑģиÑħи
    0.07
    icité
    0.07
    )))),
    0.07
    declspec
    0.07
     preg
    0.07
    -navbar
    0.07
    ";}
    0.07
    ä¸ĭéĿ¢å°ıç¼ĸ
    0.07
    Activations Density 0.113%

    No Known Activations