© 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. 16006
    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
    -flow
    -18.88
    �
    -18.38
     flow
    -18.38
     tongue
    -18.00
    _flow
    -17.88
    -co
    -17.88
     Marl
    -17.88
    -mar
    -17.88
     flows
    -17.75
    Coverage
    -17.75
    POSITIVE LOGITS
    电站
    19.75
     bomber
    18.50
     Army
    18.50
    红军
    17.63
    Army
    16.88
    电力
    16.88
     citrus
    16.75
     fighter
    16.63
    城堡
    16.38
    官兵
    16.13
    Activations Density 1.455%

    No Known Activations