© 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. 1577
    Prev
    Next
    INDEX
    Explanations

    HIV, categories, gondii

    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
     pair
    -0.07
     Pair
    -0.06
     Syr
    -0.06
    peria
    -0.06
     du
    -0.06
     dupla
    -0.06
    pair
    -0.06
    è¿Ļ对
    -0.06
    itters
    -0.06
    দà§įধ
    -0.06
    POSITIVE LOGITS
    çļĦåIJĦ个
    0.14
    åĪĴåĪĨ为
    0.13
     categorized
    0.13
    çļĦåIJĦ
    0.13
    åľ¨åIJĦ个
    0.13
    éĢīæĭ©ä¸įåIJĮçļĦ
    0.13
    çļĦåĪĨç±»
    0.12
     categories
    0.12
    åĪĨç±»
    0.12
    åľ¨ä¸įåIJĮçļĦ
    0.12
    Activations Density 1.475%

    No Known Activations