© 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. 557
    Prev
    Next
    INDEX
    Explanations

    Northern Ireland

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

    No Comments

    Negative Logits
    莆田
    -24.50
    杭州
    -22.63
     Melbourne
    -22.38
    泉州
    -21.63
    厦门市
    -21.50
    厦门
    -21.50
    福州
    -21.38
    扬州
    -21.38
     Hawai
    -20.63
    合肥
    -20.63
    POSITIVE LOGITS
     NI
    31.25
     Belfast
    31.25
    NI
    29.13
     Northern
    28.13
    Northern
    27.25
    辽宁省
    24.75
    东北
    22.13
    沈阳
    22.13
    辽宁
    21.88
     NIR
    21.50
    Activations Density 0.051%

    No Known Activations