© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15300
    Prev
    Next
    INDEX
    Explanations

    military units

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

    No Comments

    Negative Logits
    的语言
    -17.50
    外语
    -16.88
     plugins
    -16.75
    lander
    -16.63
     honour
    -16.50
    语言
    -16.25
    (Language
    -16.13
     langue
    -15.88
     royalty
    -15.75
    哙
    -15.31
    POSITIVE LOGITS
    Union
    18.63
    挽
    17.00
     Union
    17.00
     Congressional
    16.00
    Federal
    16.00
     Federal
    14.56
    emen
    14.50
     mcc
    14.31
    agraph
    14.00
    oons
    13.94
    Activations Density 0.266%

    No Known Activations