© 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. 13981
    Prev
    Next
    INDEX
    Explanations

    say measurement units

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

    No Comments

    Negative Logits
     DRAW
    -19.00
    	resource
    -18.75
     Draw
    -18.75
     drawing
    -18.63
     getResource
    -18.13
    抽
    -18.00
    DRAW
    -18.00
     draw
    -17.88
    _MATERIAL
    -17.88
    资源
    -17.75
    POSITIVE LOGITS
     column
    19.75
    column
    19.38
     columns
    18.88
     Column
    18.50
    Column
    18.38
     Definitions
    18.13
    列
    17.63
     Columns
    17.63
    定义
    17.50
    define
    17.25
    Activations Density 1.028%

    No Known Activations