© 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. 31990
    Prev
    Next
    INDEX
    Explanations

    contour lines, contemporary

    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
    ä¼ĹæīĢåij¨çŁ¥
    -0.09
    -0.08
    عث
    -0.08
    consin
    -0.07
    éļĪ
    -0.07
    urement
    -0.07
    WARD
    -0.07
    WARDS
    -0.07
    INGTON
    -0.07
    kund
    -0.07
    POSITIVE LOGITS
    ä½Ĩä¸įéĻIJäºİ
    0.12
    aneous
    0.10
    ezza
    0.10
    rovers
    0.09
    åºģ
    0.09
    à¸ģารà¸ĵà¹Į
    0.09
    enedor
    0.09
    emporary
    0.09
    ãģī
    0.08
    empor
    0.08
    Activations Density 0.045%

    No Known Activations