© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1121
    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
    煤
    -40.75
     coal
    -40.75
    煤炭
    -39.00
     Coal
    -36.75
    Coal
    -35.25
    coal
    -35.25
    煤矿
    -26.38
     code
    -26.25
    Code
    -25.50
    燃煤
    -25.50
    POSITIVE LOGITS
    军事
    20.00
     military
    17.25
     Military
    16.50
    軍
    15.69
    Military
    15.69
    手臂
    15.56
    バイ
    15.31
    箭
    15.00
    四川省
    14.94
    教育
    14.63
    Activations Density 0.053%

    No Known Activations