© 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. 13944
    Prev
    Next
    INDEX
    Explanations

    narrative elements

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

    No Comments

    Negative Logits
    航线
    -15.94
    :data
    -15.69
    Guid
    -15.69
    \data
    -15.50
    edata
    -15.50
    航行
    -15.38
     data
    -15.38
     Projects
    -15.25
    -data
    -15.25
    报销
    -15.19
    POSITIVE LOGITS
    设置
    24.13
    人物
    23.50
    刻画
    23.13
     settings
    22.38
    设
    22.38
    setting
    22.25
     plot
    22.00
    描写
    21.88
    情节
    21.75
    settings
    21.38
    Activations Density 0.369%

    No Known Activations

    This feature has no known activations.