© 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. 14291
    Prev
    Next
    INDEX
    Explanations

    non‑system tokens

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

    No Comments

    Negative Logits
    系统
    -45.25
    系统的
    -43.75
     systems
    -42.50
     system
    -42.25
    systems
    -39.75
    system
    -39.75
    系統
    -39.75
     Systems
    -37.50
    -system
    -36.75
    	system
    -36.25
    POSITIVE LOGITS
    燔
    15.25
    寄
    15.19
    forum
    14.81
    TabPage
    14.69
    法令
    14.25
    /format
    14.25
    纪委
    13.88
     forum
    13.81
     disc
    13.75
    Format
    13.75
    Activations Density 0.902%

    No Known Activations