© 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. 271
    Prev
    Next
    INDEX
    Explanations

    say "Chinese place names"

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

    No Comments

    Negative Logits
     Moscow
    -31.75
    俄
    -31.38
     Russians
    -30.88
    莫斯科
    -30.25
     Russia
    -29.75
     Russian
    -29.13
     Kremlin
    -28.88
    .ts
    -27.25
    俄罗斯
    -27.13
    在上海
    -27.00
    POSITIVE LOGITS
    南宁
    25.38
    南宁市
    23.50
    椰
    23.38
    岘
    23.00
    漓
    22.00
    邢台
    21.38
    覃
    21.38
    顺德
    21.38
     South
    20.75
    桂林
    20.75
    Activations Density 0.530%

    No Known Activations