© 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. 28748
    Prev
    Next
    INDEX
    Explanations

    codes, firmware, or technical measurements

    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
    ifax
    -0.06
    imax
    -0.06
    long
    -0.06
    ynn
    -0.06
    line
    -0.06
    amac
    -0.06
    廳
    -0.06
    ry
    -0.06
    rs
    -0.06
     Fraser
    -0.06
    POSITIVE LOGITS
    ç¥Ŀ大家
    0.08
    dge
    0.07
    licenses
    0.07
    ลัà¸ĩ
    0.07
    urvey
    0.07
    enge
    0.07
    -days
    0.07
    omal
    0.07
    english
    0.07
    áºŃn
    0.07
    Activations Density 0.001%

    No Known Activations