© 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. 1767
    Prev
    Next
    INDEX
    Explanations

    say "graph" words

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

    No Comments

    Negative Logits
     US
    -45.25
     USA
    -40.75
    US
    -40.25
    美国
    -40.00
    在美国
    -39.75
    USA
    -39.50
    -US
    -37.00
    美國
    -36.25
    美
    -35.25
    美国人
    -35.25
    POSITIVE LOGITS
    _graph
    15.31
    graph
    14.50
     graph
    13.94
    medi
    13.94
     Mathematical
    13.69
     compact
    13.63
    图表
    13.50
    域
    13.31
    Graph
    13.19
     Graph
    13.06
    Activations Density 0.495%

    No Known Activations