© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1257
    Prev
    Next
    INDEX
    Explanations

    Chinese provinces

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

    No Comments

    Negative Logits
     Tibet
    -28.25
    西藏
    -28.00
     Tibetan
    -24.88
     Mormons
    -22.63
    雪山
    -20.38
    青海省
    -19.38
    太湖
    -19.13
     Lama
    -18.75
     Himal
    -18.50
     Scotland
    -18.13
    POSITIVE LOGITS
    UIS
    17.50
    (UI
    17.38
    อล
    17.00
    羽毛
    16.88
    .UI
    16.50
    ui
    16.00
    -ui
    15.94
    uator
    15.31
    羽
    15.25
    лив
    15.19
    Activations Density 0.081%

    No Known Activations