© 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. 14285
    Prev
    Next
    INDEX
    Explanations

    say "standard"

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

    No Comments

    Negative Logits
    .databinding
    -18.00
    定义
    -17.63
    Pdf
    -17.25
     Pdf
    -17.25
     pdf
    -17.13
     reports
    -16.63
     resourceName
    -16.63
    _pdf
    -16.50
    .reporting
    -16.13
    研究报告
    -16.13
    POSITIVE LOGITS
    节
    18.75
    節
    15.88
     standards
    15.81
     станд
    15.69
    ransition
    15.31
    ocard
    14.69
    catid
    14.69
    标准化
    14.50
    标准
    14.38
    (expect
    14.13
    Activations Density 1.474%

    No Known Activations