© 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. 14192
    Prev
    Next
    INDEX
    Explanations

    say art

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

    No Comments

    Negative Logits
     Targets
    -17.63
    驱动
    -16.88
    _food
    -16.88
    .getServer
    -16.63
    管理水平
    -16.13
    Targets
    -15.94
    食品
    -15.94
    -food
    -15.88
    Drivers
    -15.75
    =read
    -15.75
    POSITIVE LOGITS
    艺术
    51.00
    绘画
    50.00
     artist
    47.75
    艺术家
    47.75
     artwork
    47.25
     painting
    46.75
     art
    46.50
     artistic
    46.25
    美术
    46.25
     artists
    45.50
    Activations Density 1.807%

    No Known Activations