© 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. 14255
    Prev
    Next
    INDEX
    Explanations

    say warfare

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

    No Comments

    Negative Logits
    callback
    -18.38
     exporters
    -17.75
    Exporter
    -17.50
     exporter
    -16.75
     Export
    -16.50
    health
    -16.50
     projector
    -16.25
     Callback
    -16.13
    ental
    -16.13
     Health
    -16.13
    POSITIVE LOGITS
    起义
    18.50
    战斗
    17.88
    建军
    17.75
    进攻
    17.63
    ��
    17.25
    作战
    17.13
    防守
    17.00
    攻
    16.63
    攻势
    15.69
    兵力
    15.56
    Activations Density 0.322%

    No Known Activations