© 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. 64921
    Prev
    Next
    INDEX
    Explanations

    direction and motion

    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
    .mods
    -0.08
    åľ¨æīĢæľī
    -0.07
    ắm
    -0.07
    ÑĢоÑģло
    -0.07
    éķ¿æŀª
    -0.07
    åħ¬åı¸èĤ¡ç¥¨
    -0.07
    è·º
    -0.06
    è¼
    -0.06
    reon
    -0.06
    truncate
    -0.06
    POSITIVE LOGITS
    çļĦè¿ĩç¨ĭä¸Ń
    0.11
     motion
    0.08
     slowly
    0.08
    è¿ĩç¨ĭä¸Ń
    0.08
    äºĨä¸Ģ段
    0.08
    å½ĵåīįä½įç½®
    0.07
     gradually
    0.07
    ä¼ļåıĹåĪ°
    0.07
     trajectory
    0.07
    çļĦéģİç¨ĭä¸Ń
    0.07
    Activations Density 0.028%

    No Known Activations