© 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. 900
    Prev
    Next
    INDEX
    Explanations

    say Washington

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

    No Comments

    Negative Logits
    惠州
    -29.00
    梅州
    -26.88
    广东
    -25.25
    汕
    -23.50
    湖州
    -23.38
    广东省
    -22.13
     Kerala
    -21.50
    江门
    -21.38
    顺德
    -21.38
    东莞
    -21.13
    POSITIVE LOGITS
     Washington
    56.00
     DC
    55.00
    华盛顿
    53.50
    Washington
    53.00
     dc
    49.00
    (dc
    47.75
    DC
    46.00
    dc
    45.75
     washington
    45.00
    北京市
    43.75
    Activations Density 0.203%

    No Known Activations