© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 3195
    Prev
    Next
    INDEX
    Explanations

    movement

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    interface
    -19.38
     mh
    -16.50
     mw
    -16.13
    设计方案
    -15.94
    stype
    -15.88
     dataset
    -15.81
     Interface
    -15.81
    MV
    -15.63
    MW
    -15.63
    andle
    -15.63
    POSITIVE LOGITS
     movement
    50.00
    movement
    46.25
     Movement
    44.25
    Movement
    42.25
    运动
    39.50
    _movement
    37.75
     movements
    33.25
     motion
    32.50
    motion
    30.88
    運動
    28.38
    Activations Density 0.187%

    No Known Activations