© 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. 15543
    Prev
    Next
    INDEX
    Explanations

    say watch

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

    No Comments

    Negative Logits
    zell
    -20.00
    炸弹
    -19.63
     venda
    -19.38
    dzi
    -18.13
    setLayout
    -17.88
    炸
    -17.88
    markup
    -17.75
    Kr
    -17.75
    殖
    -17.50
    销售
    -17.50
    POSITIVE LOGITS
    监护
    18.25
    -watch
    18.25
     watcher
    17.88
    watch
    17.50
    旁
    17.25
    贵宾
    16.88
     monitoring
    16.88
    _monitor
    16.00
     watch
    15.94
     Privacy
    15.81
    Activations Density 0.306%

    No Known Activations