© 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. 14044
    Prev
    Next
    INDEX
    Explanations

    say "ense"

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

    No Comments

    Negative Logits
     components
    -27.75
    组件
    -26.25
     component
    -26.00
    _components
    -25.88
    (components
    -25.50
     Components
    -25.13
    _COMPONENT
    -25.13
    Components
    -25.13
    .components
    -24.75
     Component
    -24.63
    POSITIVE LOGITS
    策略
    21.50
     strategies
    20.50
     strategy
    20.38
    _strategy
    18.88
    strategy
    18.75
     Strategy
    17.63
     Strategies
    16.88
    Strategy
    16.75
     scenarios
    16.00
    场景
    15.81
    Activations Density 0.626%

    No Known Activations