© 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. 3141
    Prev
    Next
    INDEX
    Explanations

    say "force"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    页面
    -17.50
     table
    -16.88
    .level
    -16.38
    أت
    -16.13
    level
    -16.00
    窗户
    -15.81
     level
    -15.75
    _Level
    -15.69
    enheim
    -15.69
    razier
    -15.63
    POSITIVE LOGITS
     force
    58.50
     Force
    52.25
    force
    52.00
    力
    50.75
    Force
    49.00
    力量
    46.25
    -force
    42.50
    _force
    41.75
     forces
    39.25
    (force
    38.75
    Activations Density 0.189%

    No Known Activations