© 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. 14284
    Prev
    Next
    INDEX
    Explanations

    say routes

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

    No Comments

    Negative Logits
    集
    -17.13
    坐着
    -16.75
    ListModel
    -16.50
     Tập
    -15.94
    竽
    -15.88
    坐下
    -15.81
    集中
    -15.63
    薮
    -15.50
    抽烟
    -15.19
    源
    -15.13
    POSITIVE LOGITS
    路由
    25.25
     route
    25.00
     routes
    24.13
    Route
    23.50
     Route
    23.13
    _routes
    22.88
    路径
    22.75
    通道
    22.63
    工程
    22.63
     infrastructure
    22.63
    Activations Density 0.878%

    No Known Activations