© 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. 548
    Prev
    Next
    INDEX
    Explanations

    say "Poland"

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

    No Comments

    Negative Logits
    三亚
    -26.38
    在香港
    -25.88
    芒果
    -24.38
    桉
    -23.00
     Rodney
    -22.38
    海南省
    -22.00
    洛杉矶
    -22.00
    珊瑚
    -22.00
    椰
    -21.75
    香港
    -21.63
    POSITIVE LOGITS
    波兰
    65.00
     Polish
    64.00
     Poland
    57.25
     Warsaw
    53.75
    安徽省
    48.25
     Ł
    45.75
    滁
    45.75
    蚌埠
    45.25
    合肥
    44.00
     Pols
    43.25
    Activations Density 0.361%

    No Known Activations