© 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. 9832
    Prev
    Next
    INDEX
    Explanations

    unicode, _literals, said

    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
    _IE
    -0.07
    æıIJä¾Ľèī¯å¥½çļĦ
    -0.07
    incu
    -0.07
    ovsky
    -0.07
    AndGet
    -0.07
    çľīå¿ĥ
    -0.07
    lessness
    -0.07
    anyi
    -0.07
    ¡
    -0.07
    psilon
    -0.07
    POSITIVE LOGITS
    ush
    0.08
    ir
    0.07
    kod
    0.07
    es
    0.07
    patch
    0.07
    USH
    0.07
    HN
    0.06
    æ¤į
    0.06
     ÙħÙĨÙĩÙħا
    0.06
    irc
    0.06
    Activations Density 0.005%

    No Known Activations