© 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. 2164
    Prev
    Next
    INDEX
    Explanations

    Serbia

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

    No Comments

    Negative Logits
    荻
    -17.75
    海岛
    -17.38
    (register
    -17.25
    sti
    -17.13
    @register
    -16.63
     pen
    -16.50
     Dough
    -16.25
    =pos
    -16.00
     reg
    -15.94
     pineapple
    -15.94
    POSITIVE LOGITS
    Ser
    37.50
     Serena
    36.75
     Ser
    36.50
     Serbia
    36.00
     Serbian
    35.75
     Serg
    31.88
    _ser
    30.63
     SER
    28.88
    SER
    27.25
    塞尔
    27.25
    Activations Density 0.019%

    No Known Activations