© 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. 106
    Prev
    Next
    INDEX
    Explanations

    Cambodia

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

    No Comments

    Negative Logits
     texas
    -29.25
     Texas
    -28.38
    Texas
    -27.75
     Iowa
    -27.25
     Illinois
    -27.00
    济宁
    -26.88
    在广州
    -26.75
     Nigerian
    -25.50
    广州
    -25.25
    广东
    -25.25
    POSITIVE LOGITS
     Hok
    30.13
    福
    25.25
     Fuji
    23.38
    GOR
    21.38
    斐
    21.25
     Sok
    20.00
    TOR
    20.00
     Orc
    20.00
    湟
    19.75
    甪
    19.63
    Activations Density 0.155%

    No Known Activations