© 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. 21395
    Prev
    Next
    INDEX
    Explanations

    verbs indicating the beginning of an action

    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
    aster
    -0.07
    ä¸Ģå¤ľ
    -0.07
    auta
    -0.07
    设为é¦ĸ页
    -0.07
    åĮĸåѦåĵģ
    -0.07
    æľºä¼ļ
    -0.07
    ì³IJ
    -0.07
    ä¸ĢæĻļ
    -0.07
    ä¹°åĪ°
    -0.07
    å¤ĦçIJĨ好
    -0.07
    POSITIVE LOGITS
    ä¼Ĭå§ĭ
    0.09
    /start
    0.09
     anew
    0.09
    åģļèµ·
    0.09
    æĸ°ä¸Ģè½®
    0.08
     본격
    0.08
    ä¹ĭåĪĿ
    0.08
     ìĭľìŀijëIJľ
    0.08
    并å¼Ģå§ĭ
    0.08
    æĸ°çļĦ
    0.08
    Activations Density 0.198%

    No Known Activations