© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 51912
    Prev
    Next
    INDEX
    Explanations

    symbols like *z + - **

    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
    ostos
    -0.08
    stadt
    -0.07
    deaux
    -0.07
    erals
    -0.07
    stur
    -0.07
    obod
    -0.06
    alda
    -0.06
    ucher
    -0.06
     à¸ŀิ
    -0.06
    ardon
    -0.06
    POSITIVE LOGITS
    utters
    0.08
     khoá
    0.08
    ç»Ĩ
    0.07
    /gallery
    0.07
    æĭīæĭī
    0.07
    åĨįæİ¥åĨį
    0.07
     khóa
    0.07
    温
    0.07
    -le
    0.07
    loch
    0.07
    Activations Density 0.010%

    No Known Activations