© 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. 31840
    Prev
    Next
    INDEX
    Explanations

    modernization and applications

    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
    ç»ıæµİè´¸æĺĵ
    -0.07
    ç»´æĮģ
    -0.07
    åѦçĶŁå·¥ä½ľ
    -0.06
     (
    -0.06
    é¢Ŀå¤ĸçļĦ
    -0.06
    æīĵåıij
    -0.06
    缸å½ĵ大çļĦ
    -0.06
    åĩłä¹İ
    -0.06
    毫æĹłçĸijéĹ®
    -0.06
    /
    -0.06
    POSITIVE LOGITS
    åĸľæĢĴåĵĢ
    0.11
    âĸ·
    0.10
    åħ¸åŀĭæ¡Īä¾ĭ
    0.10
    obet
    0.09
    常æĢģåĮĸ
    0.09
    深度èŀįåIJĪ
    0.09
    梯度
    0.09
    éĽĨèģļ
    0.09
    åĨħ涵
    0.09
     адÑĢеÑģ
    0.09
    Activations Density 0.002%

    No Known Activations