© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 16275
    Prev
    Next
    INDEX
    Explanations

    say "spi"

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

    No Comments

    Negative Logits
     Dawson
    -23.63
     Castro
    -23.38
     Sawyer
    -22.75
     Lennon
    -21.25
    hev
    -20.75
     CCC
    -20.75
    锯
    -20.63
    intValue
    -20.13
    果树
    -19.75
     Kerr
    -19.63
    POSITIVE LOGITS
     Spi
    26.50
     spi
    25.25
    精灵
    24.25
    SPI
    23.63
    Spi
    23.50
    spir
    23.13
    spi
    23.00
     Shah
    22.88
    _spi
    22.38
     SPI
    22.25
    Activations Density 6.113%

    No Known Activations