© 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. 424
    Prev
    Next
    INDEX
    Explanations

    say Chinese place names

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

    No Comments

    Negative Logits
     PIT
    -18.00
    HDR
    -17.75
    Israeli
    -17.63
     Palestinian
    -17.25
    以色列
    -16.63
    /flutter
    -16.38
    Cake
    -16.25
     MAD
    -16.13
     Palestinians
    -16.13
     Bry
    -16.13
    POSITIVE LOGITS
     Qing
    31.63
     Shanghai
    29.13
    Hong
    28.00
     Hong
    27.13
     Guang
    26.75
     China
    26.25
     Beijing
    24.88
    清朝
    24.75
    China
    24.63
     Chinese
    24.50
    Activations Density 0.291%

    No Known Activations