© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 29929
    Prev
    Next
    INDEX
    Explanations

    motion control

    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
    aso
    -0.08
    ä¼ĹæīĢåij¨çŁ¥
    -0.08
     infil
    -0.08
    ovina
    -0.08
    ç²Ĵå¾Ħ
    -0.08
    æ²¹æĿ¡
    -0.08
    -byte
    -0.07
    оек
    -0.07
    empre
    -0.07
    hada
    -0.07
    POSITIVE LOGITS
     motion
    0.11
     Motion
    0.10
     motions
    0.10
    è¿IJåĬ¨
    0.09
    motion
    0.09
    è¿IJåĬ¨çļĦ
    0.09
    çļĦè¿IJåĬ¨
    0.09
    éģĭåĭķ
    0.09
    Motion
    0.08
    -motion
    0.08
    Activations Density 0.006%

    No Known Activations