© 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. 13929
    Prev
    Next
    INDEX
    Explanations

    say film

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

    No Comments

    Negative Logits
    okit
    -19.88
     readings
    -18.38
    asurement
    -18.00
    讀
    -18.00
    دن
    -17.88
    azar
    -16.88
    -read
    -16.88
    lesen
    -16.38
    服务水平
    -16.00
     measurement
    -15.94
    POSITIVE LOGITS
     film
    48.75
     films
    48.50
    电影
    47.75
     Film
    46.25
     Films
    45.75
    Film
    44.50
    film
    44.25
    影片
    42.75
    films
    42.75
     movie
    41.75
    Activations Density 0.634%

    No Known Activations