© 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. 63460
    Prev
    Next
    INDEX
    Explanations

    deadlift

    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
    ÙĤØ©
    -0.08
    rou
    -0.08
    utherland
    -0.07
    ستاÙĨ
    -0.07
    æĬĢæľ¯è§ĦèĮĥ
    -0.07
    ingly
    -0.07
    itzer
    -0.07
    æĪ¿çļĦ
    -0.07
    è¡Įéķ¿
    -0.07
    大ä¸ĸçķĮ
    -0.07
    POSITIVE LOGITS
    wards
    0.08
    ibat
    0.07
    ../../../../
    0.07
    abcd
    0.06
    éľĦ
    0.06
    éĽ¹
    0.06
    poon
    0.06
    第äºĶ
    0.06
    teenth
    0.06
    indsay
    0.06
    Activations Density 0.009%

    No Known Activations