© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 3122
    Prev
    Next
    INDEX
    Explanations

    say island

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    组件
    -21.63
    component
    -19.50
    Component
    -18.88
    -component
    -18.75
     Component
    -18.38
    	component
    -18.13
    (component
    -18.00
    components
    -17.63
     component
    -17.63
     components
    -17.50
    POSITIVE LOGITS
     island
    24.75
    岛
    24.50
     Island
    22.25
    島
    21.13
    岛上
    21.00
     Interface
    17.13
    /domain
    17.00
    镇
    16.88
     interface
    16.38
    archy
    16.38
    Activations Density 0.067%

    No Known Activations