© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 851
    Prev
    Next
    INDEX
    Explanations

    Hong Kong

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

    No Comments

    Negative Logits
    亳
    -27.38
    轵
    -27.13
     Indiana
    -25.38
     Romania
    -24.13
     Turkey
    -22.88
     Kurdish
    -22.63
     Armenia
    -22.50
    Michigan
    -22.50
     Armenian
    -22.38
     Purdue
    -22.38
    POSITIVE LOGITS
    在香港
    64.50
    香港
    62.00
     Hong
    55.25
    Hong
    51.00
     HK
    49.00
    港
    47.25
    港澳
    46.75
    粤港澳
    43.50
    HK
    43.25
    粤
    42.25
    Activations Density 0.214%

    No Known Activations