© 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. 1649
    Prev
    Next
    INDEX
    Explanations

    say U words

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

    No Comments

    Negative Logits
     United
    -38.50
    United
    -35.50
     UNITED
    -26.25
    乌
    -20.00
    UI
    -20.00
     Ui
    -19.75
     uniform
    -19.25
     united
    -19.00
    UCT
    -18.75
    UIT
    -18.75
    POSITIVE LOGITS
     Brah
    17.75
    [image
    17.50
    土壤
    17.00
     mage
    16.88
     soil
    16.88
    <Image
    16.38
    瓷
    16.00
     Image
    15.81
     stream
    15.69
    /Image
    15.56
    Activations Density 0.103%

    No Known Activations