© 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. 14202
    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
    技术支持
    -26.00
     techniques
    -25.25
    技术
    -25.13
     Techniques
    -24.63
    和技术
    -23.50
     technique
    -23.00
     param
    -22.88
     Technique
    -22.88
    报告
    -22.75
    的技术
    -22.75
    POSITIVE LOGITS
    动生成
    19.00
    DRAW
    17.00
    äch
    16.75
    _DRAW
    16.25
     Drawing
    16.13
     drawing
    15.94
     DRAW
    15.94
    资产管理
    15.56
     Draw
    15.38
    地图
    15.31
    Activations Density 0.770%

    No Known Activations