© 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. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1980
    Prev
    Next
    INDEX
    Explanations

    Jewish

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jewish
    -39.75
     Judaism
    -36.25
     Jews
    -35.00
     jewish
    -33.75
     Jew
    -32.50
     Juda
    -25.25
     Hebrew
    -24.88
     Israel
    -24.00
    Israel
    -23.38
    犹
    -22.38
    POSITIVE LOGITS
    -card
    18.00
    武
    16.25
    卡
    16.00
     carbon
    15.94
     Carbon
    15.63
    /card
    15.31
    碳
    15.19
    Font
    14.94
    font
    14.88
     formula
    14.88
    Activations Density 0.120%

    No Known Activations