© 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. 24611
    Prev
    Next
    INDEX
    Explanations

    latex document class

    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
    ä¼łè¯´ä¸ŃçļĦ
    -0.07
    å¤ļ空
    -0.07
    зад
    -0.07
    omber
    -0.07
    ä¸įéĢı
    -0.07
    avian
    -0.07
    è¿Ļ个éģĵçIJĨ
    -0.07
    ocy
    -0.06
    ekut
    -0.06
    ukah
    -0.06
    POSITIVE LOGITS
    é¢Ĩ
    0.07
    abis
    0.07
    çŁ³éŨ
    0.07
    itek
    0.07
    éĥ½åľ¨è¿ĻéĩĮ
    0.07
    evel
    0.06
    łíĮ
    0.06
    æĺ¾
    0.06
    æĬ¥å¤į
    0.06
    rio
    0.06
    Activations Density 0.004%

    No Known Activations