© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1756
    Prev
    Next
    INDEX
    Explanations

    say "plot"

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

    No Comments

    Negative Logits
    地震
    -35.75
     earthquakes
    -33.75
     earthquake
    -32.75
    earth
    -31.75
    Earth
    -28.25
    -earth
    -27.00
     earth
    -26.88
     Earth
    -25.75
    地球
    -23.50
     earthqu
    -23.25
    POSITIVE LOGITS
    画画
    17.38
    绘画
    16.38
     plots
    16.00
     plot
    15.75
    .Play
    15.69
     Plot
    15.13
    -meta
    15.13
    Plot
    15.00
     meta
    14.88
     plotted
    14.88
    Activations Density 0.065%

    No Known Activations