© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1410
    Prev
    Next
    INDEX
    Explanations

    say "Italian"

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

    No Comments

    Negative Logits
     square
    -46.75
     Square
    -45.75
    Square
    -43.75
    square
    -38.75
     squares
    -37.50
     SQUARE
    -37.00
    平方
    -35.00
    -square
    -34.75
    _square
    -34.75
    (square
    -33.25
    POSITIVE LOGITS
    意大利
    19.25
    烨
    16.50
    电影
    16.50
     Italian
    16.13
     Dante
    16.00
     Italy
    15.44
    movie
    15.31
    خش
    15.13
     italian
    14.75
     documentary
    14.69
    Activations Density 0.068%

    No Known Activations