© 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. 18071
    Prev
    Next
    INDEX
    Explanations

    Montenegro, Satellite Award, Unidos, Michele

    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
    <|box_end|>
    -0.08
    ÑģÑĤе
    -0.07
    ledo
    -0.07
    rious
    -0.07
    пелÑĮ
    -0.07
    å¯Įè´µ
    -0.07
     gì
    -0.07
     Lump
    -0.07
     ׾׳×ķ
    -0.07
    erland
    -0.07
    POSITIVE LOGITS
    ç§ijåѦçłĶ究éĻ¢
    0.07
    aruhi
    0.06
     communiqué
    0.06
    _attempt
    0.06
    ä¸ĩå²ģ
    0.06
    ìĿ¸íĬ¸
    0.06
     distr
    0.06
    羣çļĦ太
    0.06
    intl
    0.06
    apis
    0.06
    Activations Density 0.048%

    No Known Activations