© 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. 34482
    Prev
    Next
    INDEX
    Explanations

    Turin, private, math

    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
    å§ijèĭı
    -0.07
    æ¯ıåŃ¦æľŁ
    -0.07
    æĿ¥å¾ĹåıĬ
    -0.07
    %^
    -0.07
    ]|[
    -0.07
    cho
    -0.07
    ÑįÑĢ
    -0.07
    aro
    -0.06
    splice
    -0.06
    SetColor
    -0.06
    POSITIVE LOGITS
    astery
    0.08
    .emit
    0.08
     branding
    0.07
    kurat
    0.07
    .defineProperty
    0.07
    äºĨæķ´ä¸ª
    0.07
    çĪĨåĩº
    0.07
    ãĥ©ãĥ³ãĥģ
    0.07
    ancellable
    0.07
    ãĥĨãĥ³
    0.07
    Activations Density 0.006%

    No Known Activations