© 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. 38693
    Prev
    Next
    INDEX
    Explanations

    interface or library names

    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
     phu
    -0.08
     Whip
    -0.08
    ()",
    -0.08
    åĮħ
    -0.07
    :Any
    -0.07
    velt
    -0.07
     Amat
    -0.07
    èĤ¯
    -0.07
    iale
    -0.07
    pdo
    -0.07
    POSITIVE LOGITS
     Kata
    0.07
    æľīåºı
    0.07
     AABB
    0.07
    _BU
    0.07
     sort
    0.06
     output
    0.06
    Output
    0.06
    è¾ĵåĩº
    0.06
     kata
    0.06
    éģµçºªå®Īæ³ķ
    0.06
    Activations Density 0.112%

    No Known Activations