© 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. 15473
    Prev
    Next
    INDEX
    Explanations

    say "及"

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

    No Comments

    Negative Logits
    -clean
    -16.75
     Clarkson
    -16.38
     Shen
    -16.38
     Griffin
    -15.75
     căng
    -15.50
     Crowley
    -15.44
    erton
    -15.38
     Saras
    -15.00
    flush
    -14.88
    青春
    -14.69
    POSITIVE LOGITS
    gart
    18.00
    yped
    17.63
     gamb
    16.75
    倬
    16.38
     Kidd
    16.38
    lld
    16.13
    UTE
    16.00
    LLU
    15.94
    odelist
    15.94
     ferr
    15.81
    Activations Density 0.155%

    No Known Activations