© 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. 1325
    Prev
    Next
    INDEX
    Explanations

    military

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

    No Comments

    Negative Logits
     military
    -37.75
     Military
    -37.25
    军事
    -36.25
    Military
    -34.00
     militar
    -29.63
    军
    -29.50
    軍
    -28.38
    µ
    -28.00
     milit
    -27.75
     µ
    -26.25
    POSITIVE LOGITS
    黍
    18.13
     Graham
    17.25
    csv
    16.63
    鲈
    16.63
    Csv
    16.63
     csv
    16.38
     csvfile
    16.25
    (csv
    16.13
    -TV
    16.13
    andas
    15.88
    Activations Density 0.071%

    No Known Activations