© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14856
    Prev
    Next
    INDEX
    Explanations

    say "French"

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

    No Comments

    Negative Logits
    堰
    -19.00
    木耳
    -18.75
     webhook
    -18.38
    坞
    -18.25
    塘
    -17.63
     AWS
    -17.38
     Shard
    -17.25
    硖
    -17.25
     Sheffield
    -17.25
    江东
    -17.13
    POSITIVE LOGITS
     French
    32.50
     France
    30.50
    French
    29.75
    法国
    28.63
    巴黎
    28.25
     french
    28.13
     française
    28.00
     français
    27.63
    France
    26.88
    フランス
    25.75
    Activations Density 0.722%

    No Known Activations