© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 16124
    Prev
    Next
    INDEX
    Explanations

    say military

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

    No Comments

    Negative Logits
    童话
    -22.13
    妖怪
    -20.50
     mushroom
    -18.50
    alloween
    -18.50
     granny
    -18.13
    .EventType
    -17.50
    粽子
    -17.50
     dood
    -17.38
     Esther
    -17.38
     mystery
    -17.38
    POSITIVE LOGITS
     militar
    17.88
    枪
    17.38
    军事
    16.88
     Lockheed
    16.63
     military
    16.63
     metal
    16.50
    支行
    16.38
    燧
    16.38
    国防部
    16.25
    金属
    16.13
    Activations Density 0.902%

    No Known Activations