© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15729
    Prev
    Next
    INDEX
    Explanations

    facial regions

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

    No Comments

    Negative Logits
    系统
    -22.88
    系统的
    -21.38
    系統
    -19.38
    システム
    -19.13
     system
    -19.13
    System
    -19.13
    -system
    -18.50
     System
    -17.75
    SystemService
    -17.75
    ystem
    -17.63
    POSITIVE LOGITS
    ridge
    17.38
     region
    16.88
    region
    16.75
    额头
    16.50
     regions
    16.50
     lids
    15.75
     Region
    15.44
    regions
    15.38
    conv
    15.38
     area
    15.38
    Activations Density 0.173%

    No Known Activations