© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 939
    Prev
    Next
    INDEX
    Explanations

    say "place names"

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

    No Comments

    Negative Logits
     Dallas
    -31.00
    珠海
    -28.25
     Australian
    -28.13
     Texas
    -28.00
    巴西
    -27.88
     Hawai
    -27.13
    汕头
    -26.63
    Texas
    -26.38
     Brisbane
    -26.25
     Australia
    -25.75
    POSITIVE LOGITS
    湖州
    38.50
    苏州市
    31.00
     Syracuse
    29.75
    太湖
    29.00
     Niagara
    28.63
    苏州
    28.50
    阊
    27.38
     Alps
    26.38
     Cuomo
    26.00
    嘉兴
    25.75
    Activations Density 0.161%

    No Known Activations