© 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. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 802
    Prev
    Next
    INDEX
    Explanations

    say "Chinese" words

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

    No Comments

    Negative Logits
    西班牙
    -24.50
    英格兰
    -24.38
    阿根廷
    -24.38
    丹麦
    -23.00
    比利时
    -22.63
    爱尔兰
    -22.13
    挪威
    -21.63
    墨西哥
    -21.38
    利物浦
    -20.88
    意大利
    -20.50
    POSITIVE LOGITS
     Chinese
    58.25
     Jiang
    56.50
     China
    56.50
     Beijing
    55.00
     Guang
    54.25
     yuan
    53.50
     Yuan
    52.75
     Qing
    52.00
     Tian
    51.75
    Chinese
    51.50
    Activations Density 1.704%

    No Known Activations