© 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. 449
    Prev
    Next
    INDEX
    Explanations

    say Portuguese

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

    No Comments

    Negative Logits
    暖气
    -19.88
    滑雪
    -19.88
    .Pool
    -18.25
     Ski
    -18.00
    旅馆
    -17.75
    洗手
    -17.63
    洮
    -17.38
     skiing
    -16.63
     ski
    -16.38
    场馆
    -16.38
    POSITIVE LOGITS
    葡萄牙
    31.13
    在广州
    31.00
     Portuguese
    28.38
     Portugal
    27.38
    广州
    27.00
     Lisbon
    26.50
    航海
    26.13
    广东
    26.00
    荷兰
    25.38
    肇庆
    25.00
    Activations Density 0.338%

    No Known Activations