© 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. 21127
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and code

    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
    WARE
    -0.07
    åįļ大精深
    -0.07
    èī²çļĦ
    -0.07
    oo
    -0.07
    uu
    -0.06
    halt
    -0.06
    ap
    -0.06
    zare
    -0.06
    åı¥åı¥
    -0.06
    apult
    -0.06
    POSITIVE LOGITS
    个çĤ¹
    0.09
    -wide
    0.08
    á»ij
    0.07
     number
    0.07
    gettext
    0.07
    еÑģÑģ
    0.07
    utkan
    0.07
     TRANG
    0.07
    geois
    0.07
    isata
    0.07
    Activations Density 0.003%

    No Known Activations