© 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. 59036
    Prev
    Next
    INDEX
    Explanations

    code syntax punctuation

    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
    Negative Logits
    åĪĩçļĦ
    -0.07
    åºĶæĢ¥ç®¡çIJĨå±Ģ
    -0.07
    åį´è¯´
    -0.07
    åIJĥåIJĥ
    -0.07
    æĤ¨çļĦä½įç½®
    -0.07
    Ľ
    -0.07
    æľĪä¸Ĭ
    -0.07
    emuk
    -0.07
    noinspection
    -0.07
    ä¸ĢåĪ»
    -0.07
    POSITIVE LOGITS
    ondo
    0.08
     unused
    0.07
    icola
    0.07
    ãs
    0.07
    æģ©
    0.07
    >tag
    0.07
    ingleton
    0.06
    DIC
    0.06
    ugat
    0.06
    ost
    0.06
    Activations Density 0.218%

    No Known Activations