© 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. 1104
    Prev
    Next
    INDEX
    Explanations

    say court

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    wire
    -29.63
    _wire
    -29.50
     wire
    -29.50
    Wire
    -27.50
     wires
    -25.25
     wireless
    -24.88
     Wire
    -24.38
     Wireless
    -22.75
    无线
    -20.88
    PCODE
    -20.25
    POSITIVE LOGITS
     Court
    18.13
    法院
    16.75
     English
    16.25
    Θ
    16.00
    英雄
    15.63
     Courts
    15.31
    Omega
    15.25
     Mathematical
    14.94
    人民法院
    14.81
    宫廷
    14.81
    Activations Density 0.088%

    No Known Activations