© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14533
    Prev
    Next
    INDEX
    Explanations

    Napoleonic wars

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

    No Comments

    Negative Logits
    physical
    -18.88
    物理
    -18.63
    监控
    -18.25
    iscrimination
    -17.75
    imeter
    -16.88
     monitored
    -16.50
     gdb
    -16.38
    很深
    -16.38
    ymm
    -16.38
    .watch
    -16.38
    POSITIVE LOGITS
     Napoleon
    15.06
     đảo
    13.44
     Duke
    13.38
    ា
    13.25
    bay
    13.00
    ações
    13.00
    <quote
    12.94
    EXPORT
    12.94
     Campaign
    12.81
     écrit
    12.56
    Activations Density 0.112%

    No Known Activations