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

    Neuronpedia

    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. 717
    Prev
    Next
    INDEX
    Explanations

    say Xinjiang

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

    No Comments

    Negative Logits
     Osaka
    -27.38
    大阪
    -24.75
    太原
    -23.25
    宜宾
    -22.75
    在日本
    -22.13
    阎
    -21.38
     Bav
    -21.13
     Naruto
    -20.50
     Japan
    -20.38
     Japanese
    -20.38
    POSITIVE LOGITS
    新疆
    57.00
    乌鲁木齐
    47.00
     Uzbek
    38.25
    馕
    38.25
    自治区
    35.75
    喀
    34.50
    乌鲁木
    34.00
    兵团
    34.00
    乌鲁
    31.75
    疆
    31.63
    Activations Density 0.093%

    No Known Activations