© 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. 386
    Prev
    Next
    INDEX
    Explanations

    say islands

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

    No Comments

    Negative Logits
    剃
    -20.13
    毡
    -17.88
     Egyptians
    -17.75
    饮料
    -17.25
    出汗
    -17.25
    shirt
    -17.13
     drib
    -16.88
    _hr
    -16.50
     cigar
    -16.50
    酱
    -16.38
    POSITIVE LOGITS
    南海
    26.13
    岛屿
    22.25
    岛
    21.88
    群岛
    20.75
     Guam
    20.75
    Sea
    20.63
     Sea
    20.38
    海军
    20.25
     Filip
    19.88
     Honolulu
    19.75
    Activations Density 0.096%

    No Known Activations