© 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. 81
    Prev
    Next
    INDEX
    Explanations

    place names

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

    No Comments

    Negative Logits
    舟山
    -31.38
    宁波
    -30.25
    南通
    -29.13
    鄞
    -28.25
    海域
    -27.25
     ε
    -26.88
    浜
    -26.38
    海岛
    -26.13
     Bergen
    -26.00
    貝
    -26.00
    POSITIVE LOGITS
    长沙
    35.50
    长沙市
    32.75
    湖南
    32.50
    湖南省
    32.00
    太原
    31.63
     Dallas
    31.38
    衡阳
    31.25
     Houston
    30.88
    Texas
    30.50
    济南市
    30.50
    Activations Density 0.794%

    No Known Activations