© 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. 57334
    Prev
    Next
    INDEX
    Explanations

    default values and properties

    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
    urious
    -0.07
    ê¹IJ
    -0.07
    erait
    -0.07
    è¿Ļæł·æĤ¨å°±åı¯ä»¥
    -0.07
    å¯ĨåĪĩéħįåIJĪ
    -0.07
    hhh
    -0.07
    astas
    -0.07
    ×IJÖ·
    -0.07
    ยà¸Ļà¸ķà¹Į
    -0.07
    oret
    -0.07
    POSITIVE LOGITS
    ting
    0.10
    enance
    0.09
    Ùĭ
    0.09
    ÙĬØ©
    0.09
    æĥħåĨµä¸ĭ
    0.09
    ìĭľíĶ¼
    0.09
    cy
    0.08
    sWith
    0.08
    zionali
    0.08
    /default
    0.08
    Activations Density 0.032%

    No Known Activations