© 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. 1376
    Prev
    Next
    INDEX
    Explanations

    say "Chinese words"

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

    No Comments

    Negative Logits
     Pakistan
    -28.25
    Pakistan
    -26.50
     Muslim
    -24.00
    西域
    -23.88
     Pakistani
    -23.75
    伊斯兰
    -23.75
    巴基斯坦
    -22.88
    新疆
    -22.88
     pakistan
    -22.63
    Muslim
    -21.38
    POSITIVE LOGITS
    有色金属
    17.00
     Coding
    16.88
    魚
    16.75
    鱼
    16.75
    汞
    16.50
     fish
    16.38
    鱼类
    16.25
    编码
    16.00
     codes
    15.75
     numerical
    15.75
    Activations Density 0.075%

    No Known Activations