© 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. 13979
    Prev
    Next
    INDEX
    Explanations

    say "packages"

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

    No Comments

    Negative Logits
    设计
    -17.13
    hotmail
    -16.88
     EventType
    -16.00
    hoff
    -16.00
     strain
    -15.88
    _movement
    -15.81
    EventType
    -15.75
    stress
    -15.75
    经济损失
    -15.69
    输入
    -15.63
    POSITIVE LOGITS
    包
    38.50
     packages
    37.75
     Packages
    33.75
    Packages
    33.75
    -package
    33.00
    packages
    32.75
    _PACKAGE
    32.75
     package
    32.75
    .Package
    32.50
    .pkg
    32.50
    Activations Density 0.327%

    No Known Activations