© 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. 13977
    Prev
    Next
    INDEX
    Explanations

    say Exp

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

    No Comments

    Negative Logits
     production
    -29.50
    生产
    -29.13
    生产的
    -26.88
     Production
    -26.50
     process
    -26.38
     Process
    -26.25
    生产和
    -25.88
    Production
    -25.75
     producción
    -25.50
    process
    -25.00
    POSITIVE LOGITS
     configurations
    19.75
    配置
    19.50
     configuration
    19.25
    规划设计
    19.00
    探测
    18.75
     configure
    18.63
    设计方案
    18.00
     Configuration
    17.75
    configs
    17.63
    -config
    17.50
    Activations Density 0.969%

    No Known Activations