© 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. 39
    Prev
    Next
    INDEX
    Explanations

    say Guangdong

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

    No Comments

    Negative Logits
    匈
    -25.88
    奥地利
    -23.50
     Spokane
    -23.00
     Austrian
    -22.38
     Kazakhstan
    -22.25
    桧
    -21.63
     Armenian
    -21.50
    湟
    -21.38
    青海省
    -21.38
     Hungarian
    -21.13
    POSITIVE LOGITS
    广东省
    70.00
    在广州
    69.00
    粤
    67.00
    广东
    66.50
    岭南
    64.50
    广州
    63.75
    广州市
    62.00
    惠州
    57.75
    珠江
    57.25
    珠三角
    56.50
    Activations Density 0.442%

    No Known Activations