© 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. 700
    Prev
    Next
    INDEX
    Explanations

    Sri Lanka

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

    No Comments

    Negative Logits
    宝鸡
    -29.38
     Mexicans
    -27.13
    西安市
    -26.63
    Mex
    -25.88
    (px
    -25.75
    陕西
    -25.50
    泾
    -25.50
     PX
    -25.38
     Iowa
    -25.25
    重庆
    -25.25
    POSITIVE LOGITS
     Sri
    44.25
     Lanka
    38.75
    漳州
    37.00
     Tamil
    30.63
     Myanmar
    29.50
    闽
    28.75
    琉
    27.88
    泉州
    27.50
    缅甸
    27.00
    椰
    26.88
    Activations Density 0.090%

    No Known Activations