© 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. 12298
    Prev
    Next
    INDEX
    Explanations

    X-linked genetic disorders

    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
    å½¢
    -0.08
    å½¢çļĦ
    -0.07
    æĭį
    -0.07
    寿
    -0.07
    stdClass
    -0.07
     COMPR
    -0.07
    isman
    -0.07
     Hug
    -0.06
    æĭ¥æĬ±
    -0.06
     sehat
    -0.06
    POSITIVE LOGITS
    çľ¼åħī
    0.08
     Segu
    0.08
    aye
    0.08
     hại
    0.08
    धि
    0.07
    defs
    0.07
    åIJĮå·¥
    0.07
     Circuito
    0.07
    建ä¸ļ
    0.07
    opin
    0.07
    Activations Density 0.012%

    No Known Activations