© 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. 14246
    Prev
    Next
    INDEX
    Explanations

    say "draw" words

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

    No Comments

    Negative Logits
    配置
    -27.38
     configuration
    -24.50
     Configuration
    -22.50
     config
    -22.25
     generator
    -21.63
    ��
    -21.50
     Config
    -21.38
    布置
    -21.25
    Configuration
    -21.00
     IConfiguration
    -20.75
    POSITIVE LOGITS
     drawing
    16.38
    draw
    16.38
     draw
    16.13
    报道
    15.69
     draws
    15.19
     unit
    15.13
    吸取
    14.94
    写作
    14.50
     units
    14.38
    (unit
    14.31
    Activations Density 1.239%

    No Known Activations