© 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. 18670
    Prev
    Next
    INDEX
    Explanations

    months or Seattle or Page

    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
    és
    -0.08
    Vu
    -0.07
     Mits
    -0.07
    _matched
    -0.07
    èĭ±æĸĩåIJįåŃĹ
    -0.07
    zy
    -0.07
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    -0.07
    ingu
    -0.07
     av
    -0.06
    rait
    -0.06
    POSITIVE LOGITS
    æĸ°åĬłåĿ¡
    0.09
    åĬłæĭ¿å¤§
    0.08
    ä¼ĹæīĢåij¨çŁ¥
    0.07
    ayah
    0.07
     [].
    0.07
    ordan
    0.06
    bach
    0.06
    ä¸Ĭå°Ĩ
    0.06
    IDO
    0.06
    ä¸ĢçĽ´åľ¨
    0.06
    Activations Density 0.005%

    No Known Activations