© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 377
    Prev
    Next
    INDEX
    Explanations

    say foreign proper nouns

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

    No Comments

    Negative Logits
     Jiang
    -41.25
     Beijing
    -41.00
     Qin
    -37.75
     Guang
    -37.75
     Feng
    -37.00
     Qing
    -36.50
     yuan
    -36.50
     Zhao
    -36.00
     Jin
    -35.50
     Xia
    -35.50
    POSITIVE LOGITS
    伊斯
    29.25
    英格兰
    26.63
    乔治
    26.25
    欧洲
    25.25
    西班牙
    25.13
    拉丁
    24.63
    约翰
    24.25
    希腊
    24.13
    地中海
    23.88
    阿根廷
    23.38
    Activations Density 2.480%

    No Known Activations