© 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. 49423
    Prev
    Next
    INDEX
    Explanations

    table cell data TD

    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
    .dds
    -0.08
    keer
    -0.08
    ultipart
    -0.07
    .qq
    -0.07
    /token
    -0.07
    DDS
    -0.07
    æĢĢ
    -0.07
    æĩ·
    -0.07
    éĿŀåIJĮ
    -0.07
    intai
    -0.07
    POSITIVE LOGITS
    undy
    0.07
    esser
    0.07
    ä¼ļåıĺ
    0.06
    ESCO
    0.06
    elsing
    0.06
    igo
    0.06
    ä¸Ĭä¸Ģ
    0.06
     wobec
    0.06
    ponsor
    0.06
    奴
    0.06
    Activations Density 0.112%

    No Known Activations