© 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. 1849
    Prev
    Next
    INDEX
    Explanations

    written forms

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

    No Comments

    Negative Logits
    书
    -24.88
    書
    -23.25
     book
    -21.25
     Book
    -18.88
    书中
    -18.75
    书写
    -18.50
    Interface
    -17.88
     Interface
    -17.75
    (book
    -17.38
     books
    -17.25
    POSITIVE LOGITS
    cro
    18.13
    摄影
    16.88
     fotograf
    16.88
     MP
    16.63
    _PHOTO
    16.50
    QP
    16.50
    Phot
    16.50
     Photograph
    16.38
    Ps
    16.00
     Barnett
    16.00
    Activations Density 0.063%

    No Known Activations