© 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. 490
    Prev
    Next
    INDEX
    Explanations

    island names

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

    No Comments

    Negative Logits
    在广州
    -29.38
     Ontario
    -29.38
    梅州
    -28.88
    广州市
    -28.25
    广州
    -27.75
    重庆
    -27.25
    惠州
    -26.13
     Illinois
    -25.25
    广东省
    -25.13
    重庆市
    -25.00
    POSITIVE LOGITS
     Tasmania
    34.00
     Madagascar
    31.25
     Tas
    31.25
     Hob
    28.75
     Belarus
    24.63
    洱
    23.50
    大理
    21.75
     Alban
    21.50
    噶
    21.00
     Kosovo
    20.38
    Activations Density 0.071%

    No Known Activations