© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1918
    Prev
    Next
    INDEX
    Explanations

    [book] => [book]

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

    No Comments

    Negative Logits
    书
    -52.50
     book
    -50.50
     Book
    -48.75
    Book
    -47.75
     BOOK
    -47.50
     books
    -47.25
    书籍
    -46.75
    -book
    -45.50
     Books
    -45.00
    BOOK
    -44.75
    POSITIVE LOGITS
    enes
    16.13
    粒子
    15.50
     dynamic
    15.00
    logger
    15.00
    激光
    14.94
    Particle
    14.81
     matlab
    14.69
     magnetic
    14.63
    udio
    14.50
    军事
    14.44
    Activations Density 0.243%

    No Known Activations