© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1654
    Prev
    Next
    INDEX
    Explanations

    UK place names

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

    No Comments

    Negative Logits
     England
    -35.75
    英格兰
    -35.50
    英国
    -35.50
    England
    -34.00
    英
    -33.25
    英國
    -30.75
     British
    -30.13
    British
    -29.88
     English
    -29.13
    Britain
    -28.75
    POSITIVE LOGITS
    -token
    16.13
    .getToken
    15.06
    设计
    14.94
    .Bus
    14.69
     économ
    14.69
    token
    14.69
    ión
    14.50
    -Token
    14.50
    軟體
    14.44
    经济
    14.19
    Activations Density 0.389%

    No Known Activations