© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 639
    Prev
    Next
    INDEX
    Explanations

    islands

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

    No Comments

    Negative Logits
    邢台
    -26.75
    邯郸
    -24.50
    湘
    -22.88
    漯
    -22.75
    柞
    -22.75
     Damascus
    -21.38
    是韩国
    -21.25
     Korea
    -21.25
    株洲
    -20.63
    బ
    -20.50
    POSITIVE LOGITS
    岛上
    44.50
    岛
    41.00
     island
    41.00
    岛屿
    39.00
     islands
    37.75
    島
    36.75
    群岛
    36.50
     Islands
    34.25
     Island
    34.25
    海岛
    33.50
    Activations Density 0.189%

    No Known Activations