© 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. 50327
    Prev
    Next
    INDEX
    Explanations

    movement and locomotion

    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
    æķ²åĵį
    -0.08
     exposures
    -0.07
    çĭĻåĩ»
    -0.06
    çľīå¿ĥ
    -0.06
    è¿Ļç§įåģļæ³ķ
    -0.06
    跳水
    -0.06
    ware
    -0.06
     fizz
    -0.06
     rece
    -0.06
    åŃ¦ä¹łæ°ĽåĽ´
    -0.06
    POSITIVE LOGITS
     пеÑĢедви
    0.12
     movement
    0.12
    èĩªå¦Ĥ
    0.12
    éĢŁåº¦
    0.11
     propulsion
    0.11
     locom
    0.11
     motion
    0.11
     speed
    0.11
    代æŃ¥
    0.10
    çļĦ移åĬ¨
    0.10
    Activations Density 0.166%

    No Known Activations