© 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. 40563
    Prev
    Next
    INDEX
    Explanations

    over, under, while

    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
    rauch
    -0.08
    ãĤĬè¿Ķ
    -0.08
    moni
    -0.07
    TRACT
    -0.07
    etan
    -0.07
    puter
    -0.07
    ropp
    -0.07
    abora
    -0.07
    ações
    -0.07
    åŃ©åŃIJçļĦæĪIJéķ¿
    -0.07
    POSITIVE LOGITS
     fucking
    0.07
    ï½ŀãĢĤ
    0.07
    éħįç½®æĸ¹éĿ¢
    0.07
    uth
    0.07
    /of
    0.06
    (er
    0.06
    /from
    0.06
    ä»Ģä¹ĪçļĦ
    0.06
    æľįåĬ¡æ¨¡å¼ı
    0.06
    ãĢħãģ¯
    0.06
    Activations Density 0.338%

    No Known Activations