© 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. 1871
    Prev
    Next
    INDEX
    Explanations

    say port

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

    No Comments

    Negative Logits
     math
    -72.50
    数学
    -72.50
     mathematical
    -66.50
    Math
    -64.00
     Math
    -63.50
    math
    -63.25
     mathematics
    -61.00
    (math
    -60.50
     Mathematical
    -58.50
     mathematic
    -57.75
    POSITIVE LOGITS
     port
    16.75
    -port
    15.56
    sal
    15.31
    Port
    14.63
     sil
    14.63
    港口
    14.56
    reon
    14.50
     PORT
    14.44
     poj
    14.25
     Silicon
    14.00
    Activations Density 0.154%

    No Known Activations