© 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. 742
    Prev
    Next
    INDEX
    Explanations

    say Wales

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

    No Comments

    Negative Logits
     Dallas
    -26.25
    浦东
    -26.13
    长安
    -22.38
    西安
    -22.25
     Boca
    -21.63
     Tehran
    -21.50
    bian
    -21.50
    在上海
    -20.75
     Iranians
    -20.13
     Gian
    -19.75
    POSITIVE LOGITS
     Welsh
    51.75
     Wales
    47.25
     Cardiff
    33.75
     Swansea
    29.75
    Wel
    29.13
     WV
    28.25
    滇
    27.63
    佤
    27.50
    彝
    27.25
    洱
    25.38
    Activations Density 0.043%

    No Known Activations