© 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. 13992
    Prev
    Next
    INDEX
    Explanations

    say "draw"

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

    No Comments

    Negative Logits
    management
    -19.13
    管理
    -18.75
     Management
    -17.75
     trainers
    -16.63
    (score
    -16.50
     integration
    -16.50
    TEGR
    -16.50
     management
    -16.38
     Integration
    -16.25
    资产管理
    -16.00
    POSITIVE LOGITS
     draw
    18.88
     pull
    17.50
    drawing
    17.38
    draw
    17.13
     drawing
    17.00
     draws
    17.00
     drawn
    16.75
    绘制
    16.75
     isolate
    16.50
    支
    16.50
    Activations Density 1.075%

    No Known Activations