© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 268
    Prev
    Next
    INDEX
    Explanations

    say "French"

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

    No Comments

    Negative Logits
    吉林省
    -23.75
    黑龙江
    -23.75
    吉林
    -22.88
     Arizona
    -22.88
    珲
    -21.63
     Akron
    -20.88
    长春
    -20.75
    烟台
    -20.38
    Arizona
    -20.00
    黑龙江省
    -20.00
    POSITIVE LOGITS
     French
    65.50
    法国
    65.00
     France
    61.75
    French
    61.25
    巴黎
    59.00
    フランス
    58.00
    France
    56.50
     french
    54.00
     Paris
    53.75
    Paris
    49.75
    Activations Density 2.470%

    No Known Activations