© 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. 612
    Prev
    Next
    INDEX
    Explanations

    say "Celtic"

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

    No Comments

    Negative Logits
     Mohammad
    -31.50
     Mohammed
    -28.13
     Hassan
    -27.75
    印尼
    -27.38
    马来西亚
    -27.25
    迪拜
    -27.13
     Kuala
    -26.63
    在广州
    -26.38
    伊斯兰
    -26.00
    茂名
    -25.75
    POSITIVE LOGITS
     Celtic
    34.75
     Druid
    32.25
     Celt
    30.63
     Welsh
    29.38
     Gael
    25.63
     Wales
    25.50
    爱尔兰
    25.13
     Gaul
    24.63
     Irish
    23.50
     Ireland
    22.75
    Activations Density 0.212%

    No Known Activations