© 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. 56004
    Prev
    Next
    INDEX
    Explanations

    rotates or moves

    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
    溢
    -0.08
     capitalized
    -0.07
     Waiting
    -0.07
    溢åĩº
    -0.07
    æī¼
    -0.07
    onian
    -0.07
    áĭ«
    -0.07
     waiting
    -0.06
     пÑĢопÑĥÑģка
    -0.06
     appeal
    -0.06
    POSITIVE LOGITS
    移åĬ¨
    0.14
     movement
    0.14
    移åĭķ
    0.13
    çļĦ移åĬ¨
    0.12
    movement
    0.12
     movements
    0.12
    moving
    0.12
    移åĬ¨çļĦ
    0.11
     ìĿ´ëıĻ
    0.11
    è¿IJåĬ¨
    0.11
    Activations Density 0.158%

    No Known Activations