© 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. 1245
    Prev
    Next
    INDEX
    Explanations

    say software terms

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

    No Comments

    Negative Logits
     law
    -51.25
    法律
    -44.75
     Law
    -43.75
    law
    -42.25
    法
    -39.75
    Law
    -38.00
    法制
    -37.50
    -law
    -37.00
    法律法规
    -37.00
     laws
    -36.75
    POSITIVE LOGITS
    excel
    21.00
    Excel
    18.38
    socket
    18.00
    _excel
    17.88
     socket
    17.25
     Excel
    16.63
    Socket
    16.25
     SOCKET
    15.63
    ELS
    15.06
    idden
    15.00
    Activations Density 0.116%

    No Known Activations