© 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. 884
    Prev
    Next
    INDEX
    Explanations

    say "British"

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

    No Comments

    Negative Logits
    合肥
    -29.63
    合肥市
    -29.50
    淮南
    -28.25
    蚌埠
    -28.25
    安徽省
    -27.25
    滁
    -26.75
    皖
    -25.00
     Boise
    -24.75
     Milwaukee
    -24.63
    安徽
    -23.88
    POSITIVE LOGITS
    英国
    22.38
    詹姆
    22.13
    詹姆斯
    22.00
     Cornwall
    21.50
     Halifax
    21.00
     البريطاني
    20.63
    Virginia
    20.63
     £
    20.25
    英國
    20.13
     Virginia
    19.50
    Activations Density 0.424%

    No Known Activations