© 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. 223
    Prev
    Next
    INDEX
    Explanations

    say "Chinese characters"

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

    No Comments

    Negative Logits
     Hamburg
    -23.63
    德国
    -23.50
     Munich
    -23.00
    丹麦
    -21.75
    ドイツ
    -21.13
     Berlin
    -21.00
    柏林
    -20.88
    鲁迅
    -20.38
    基辅
    -20.13
     Ludwig
    -20.00
    POSITIVE LOGITS
    寨
    17.25
    壶
    16.75
     Ca
    16.13
    opp
    15.94
    岷
    15.63
    CAC
    15.56
     Elk
    15.56
    泸
    15.44
    PWD
    15.38
    洱
    15.31
    Activations Density 0.140%

    No Known Activations