© 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. 784
    Prev
    Next
    INDEX
    Explanations

    say "华为"

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

    No Comments

    Negative Logits
     Asheville
    -25.75
    Virginia
    -23.00
     Raleigh
    -22.00
    榉
    -21.88
     Virginia
    -21.88
     Appalachian
    -21.13
    辽宁省
    -21.00
     Charlottesville
    -21.00
     Durham
    -20.75
     Appalach
    -20.25
    POSITIVE LOGITS
    华为
    54.00
     Huawei
    51.50
    Hu
    38.25
    .hu
    31.38
     Hong
    30.75
    在深圳
    29.63
     Hu
    29.25
    蜀
    29.00
    Hong
    28.88
     hu
    28.25
    Activations Density 0.056%

    No Known Activations