© 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. 1807
    Prev
    Next
    INDEX
    Explanations

    [山东] => [山东]

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

    No Comments

    Negative Logits
    山东
    -35.50
     Sweden
    -31.13
    山东省
    -30.75
    齐鲁
    -29.38
     Swedish
    -28.75
    Sweden
    -28.63
     Scandin
    -27.13
    瑞典
    -26.63
     Scandinavian
    -25.63
     Svens
    -22.50
    POSITIVE LOGITS
     JavaScript
    18.75
    javascript
    18.75
    JavaScript
    18.25
    张家界
    18.13
    茶
    17.13
     circle
    16.88
    茶园
    16.75
     javascript
    16.13
    茶叶
    15.94
    脚
    15.88
    Activations Density 0.109%

    No Known Activations