© 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. 27475
    Prev
    Next
    INDEX
    Explanations

    download

    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
    ë¥
    -0.08
     frustra
    -0.08
    zilla
    -0.07
    à¸Ĩ
    -0.07
    insen
    -0.07
    HING
    -0.07
    åıĬæŶæİĮæı¡
    -0.07
    ohn
    -0.06
    éĤ£åIJį
    -0.06
    normalized
    -0.06
    POSITIVE LOGITS
    ಣ
    0.07
    eph
    0.07
    лона
    0.07
     вид
    0.06
     Chattanooga
    0.06
    å®ŀ践活åĬ¨
    0.06
     Orr
    0.06
    -ed
    0.06
    ouc
    0.06
    -de
    0.06
    Activations Density 0.055%

    No Known Activations