© 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. 20200
    Prev
    Next
    INDEX
    Explanations

    options: a, b, c, d

    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
    ä¸įéķ¿
    -0.09
    ä¹Łä¸įåı¯èĥ½
    -0.08
     ngược
    -0.08
    .Layout
    -0.08
    ignor
    -0.07
    åŁºæľ¬åĬŁ
    -0.07
     Herc
    -0.07
    æľ¬æĬ¥è®¯
    -0.07
    ostos
    -0.07
     ÐŀÐŁ
    -0.07
    POSITIVE LOGITS
    ide
    0.06
    宿
    0.06
    两èĢħ
    0.06
    ibrary
    0.06
    TZ
    0.06
    azine
    0.06
    tat
    0.06
    ä¸Ĭæ¼Ķ
    0.06
    der
    0.06
    åĸī
    0.06
    Activations Density 0.003%

    No Known Activations