© 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. 1415
    Prev
    Next
    INDEX
    Explanations

    salmon

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

    No Comments

    Negative Logits
    _xml
    -29.38
    XML
    -29.25
     Salmon
    -27.88
     XML
    -27.00
    Xml
    -26.50
    xml
    -25.88
    _XML
    -25.25
     salmon
    -24.88
     xml
    -24.63
     Xml
    -23.13
    POSITIVE LOGITS
     math
    23.25
     maths
    19.63
     breath
    18.50
     culture
    18.38
     mathematical
    18.25
     cultures
    18.13
    数学
    17.88
    math
    17.75
     breathe
    17.50
     Heath
    17.50
    Activations Density 0.132%

    No Known Activations