© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 959
    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
    酒精
    -23.50
    酒业
    -23.25
    酒
    -22.75
     vodka
    -21.75
     heroin
    -21.63
     Alcohol
    -21.38
    喝酒
    -20.75
    饮酒
    -20.63
     alcohol
    -20.50
    酿酒
    -20.38
    POSITIVE LOGITS
     XML
    53.25
     xml
    51.50
    (xml
    50.75
    (XML
    49.75
     Xml
    49.50
    XML
    48.75
    .xml
    48.75
    _xml
    47.75
    /xml
    47.75
    Xml
    46.25
    Activations Density 0.148%

    No Known Activations