© 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. 14018
    Prev
    Next
    INDEX
    Explanations

    say "ast"

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

    No Comments

    Negative Logits
     paintings
    -22.88
    -upload
    -21.50
    TouchEvent
    -21.13
    油画
    -20.25
     Ethernet
    -20.25
    -response
    -19.88
    屏幕
    -19.88
     screenshots
    -19.88
     painting
    -19.50
    壁画
    -19.50
    POSITIVE LOGITS
     ast
    26.50
    (ast
    26.13
    _ast
    24.13
    Ast
    24.13
     expr
    24.13
     AST
    23.38
    表达
    23.13
     expressions
    23.00
    Expr
    22.88
    _AST
    22.88
    Activations Density 0.375%

    No Known Activations