© 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. 1496
    Prev
    Next
    INDEX
    Explanations

    say "XML"

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

    No Comments

    Negative Logits
     internet
    -47.75
     Internet
    -45.50
    Internet
    -45.25
    互联网
    -43.50
    internet
    -41.50
    インターネット
    -39.50
     INTERN
    -31.75
     Интернет
    -31.50
     интернет
    -30.88
    INTERN
    -27.38
    POSITIVE LOGITS
    XML
    16.38
    xml
    16.00
    茶
    15.56
    rus
    15.19
     XML
    15.19
     xml
    15.13
    _xml
    14.31
    Xml
    14.31
     Xml
    14.25
    <Scalar
    13.63
    Activations Density 0.125%

    No Known Activations