© 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. 565
    Prev
    Next
    INDEX
    Explanations

    say "Lao" characters

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

    No Comments

    Negative Logits
    黑龙江
    -24.50
    黑龙江省
    -24.13
     Russia
    -23.25
     Ivan
    -22.38
     Russian
    -21.50
    Russian
    -21.25
     Kremlin
    -20.25
     Greece
    -20.13
     Brazil
    -19.88
    俄罗斯
    -19.88
    POSITIVE LOGITS
    十堰
    27.00
    �
    26.38
     wx
    26.38
    襄阳
    26.25
    厦门市
    26.00
    ກ
    25.50
    ບ
    24.50
    =wx
    24.50
    (wx
    24.38
    ພ
    24.25
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.