© 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. 32499
    Prev
    Next
    INDEX
    Explanations

    cyrillic or latin word fragment

    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
    大åIJĥ
    -0.09
    udeau
    -0.08
    áva
    -0.08
    jaz
    -0.08
     Poste
    -0.08
    ÑĩÑĸ
    -0.07
     alasti
    -0.07
    大çĻ½
    -0.07
    IZER
    -0.07
    abler
    -0.07
    POSITIVE LOGITS
    çļĦäºĨ
    0.10
    çļĦåij¢
    0.09
    ìĿĺ
    0.08
    çļĦåħ¨
    0.07
    çļĦä¸Ģæł·
    0.07
    ãģª
    0.07
    çļĦåĴĮ
    0.07
    å¸ĮæľĽå¯¹æĤ¨
    0.06
    çļĦä¸Ģ
    0.06
    __*/
    0.06
    Activations Density 0.093%

    No Known Activations