© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1508
    Prev
    Next
    INDEX
    Explanations

    island

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

    No Comments

    Negative Logits
     islands
    -33.25
     island
    -33.00
    岛屿
    -32.00
     Island
    -29.88
     Islands
    -29.38
    岛
    -28.50
    海岛
    -26.38
     Islanders
    -25.63
    島
    -25.63
    岛上
    -24.25
    POSITIVE LOGITS
    菜
    17.63
     kim
    16.13
    _doc
    16.13
    .Mvc
    15.94
    etic
    15.81
    财务
    15.81
     Docs
    15.50
    作文
    15.13
    _vect
    15.06
     DOC
    15.06
    Activations Density 0.109%

    No Known Activations