© 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. 512
    Prev
    Next
    INDEX
    Explanations

    say "鲁"

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

    No Comments

    Negative Logits
     Canter
    -18.00
     Pyongyang
    -17.38
    diamond
    -16.88
    坩
    -16.75
    DOMNode
    -16.50
     kè
    -16.25
    /DD
    -16.00
    呼和浩特
    -15.75
     diamond
    -15.69
    IOC
    -15.50
    POSITIVE LOGITS
    鲁
    68.00
    魯
    58.50
     Ru
    42.00
     ru
    41.25
     RU
    41.25
    RU
    40.50
    Ru
    40.00
    ru
    39.75
     Lu
    39.25
     LU
    38.00
    Activations Density 0.060%

    No Known Activations