© 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. 14150
    Prev
    Next
    INDEX
    Explanations

    say "theater"

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

    No Comments

    Negative Logits
     densities
    -19.13
     density
    -16.50
    dens
    -16.38
    测绘
    -16.25
    favicon
    -15.69
    sdk
    -15.63
    _CSR
    -15.44
    测量
    -15.38
     Documents
    -15.31
    олов
    -15.19
    POSITIVE LOGITS
    演出
    45.00
    表演
    41.75
    演
    36.00
    演员
    36.00
    演艺
    35.75
    剧场
    35.50
     theatre
    35.25
     actor
    35.00
    剧院
    35.00
    戏剧
    33.75
    Activations Density 0.674%

    No Known Activations