© 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. 51729
    Prev
    Next
    INDEX
    Explanations

    white, colour, 5

    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
    lauf
    -0.07
    (zip
    -0.07
    头ä¸ĬçļĦ
    -0.07
    ิà¹Īà¸Ļ
    -0.06
    纶
    -0.06
     Lyons
    -0.06
     пÑĢинÑĨипи
    -0.06
    fic
    -0.06
    çŁ¥éģĵåIJĹ
    -0.06
    Ả
    -0.06
    POSITIVE LOGITS
    unks
    0.09
    andr
    0.08
    igans
    0.08
    DEFAULT
    0.08
    è§ģ人
    0.08
    é£Ľãģ°
    0.08
    opers
    0.08
    plevel
    0.07
    enges
    0.07
    ModelState
    0.07
    Activations Density 0.011%

    No Known Activations