© 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. 13956
    Prev
    Next
    INDEX
    Explanations

    say work

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

    No Comments

    Negative Logits
     buys
    -15.31
    院院长
    -15.06
    买车
    -15.00
    ELCOME
    -14.50
    AccessException
    -14.38
     TripAdvisor
    -14.19
    .tests
    -13.94
    vented
    -13.81
     trademarks
    -13.69
    鹬
    -13.69
    POSITIVE LOGITS
    工作
    69.50
     work
    69.50
    工作的
    64.50
     Work
    63.00
    work
    62.50
    工作任务
    62.25
    Work
    60.75
    的工作
    60.00
    	work
    59.00
    _work
    58.75
    Activations Density 3.518%

    No Known Activations