© 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. 1694
    Prev
    Next
    INDEX
    Explanations

    say "graph"

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

    No Comments

    Negative Logits
     publication
    -30.38
     Publishing
    -28.75
     publishing
    -28.38
     publications
    -28.38
     published
    -27.88
     publish
    -27.50
    Publish
    -27.50
     publishes
    -26.38
     Publish
    -26.13
     Publication
    -25.13
    POSITIVE LOGITS
     graph
    17.63
     CODE
    16.75
    Graph
    16.75
    graph
    16.50
     Food
    16.38
    _sym
    16.38
    .graph
    16.00
     graphs
    16.00
    sym
    16.00
    _graph
    15.88
    Activations Density 0.121%

    No Known Activations