© 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. 16278
    Prev
    Next
    INDEX
    Explanations

    say "progress"

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

    No Comments

    Negative Logits
    开了
    -17.63
    ksi
    -16.00
     kup
    -15.50
     grpc
    -14.81
     Gol
    -14.56
     mustard
    -14.25
    -gl
    -14.00
    licts
    -13.94
    reducers
    -13.88
     UIP
    -13.81
    POSITIVE LOGITS
    atura
    17.25
    ATAR
    16.63
    vidence
    16.38
     Progress
    16.00
    atur
    15.75
    ayer
    15.75
    交叉
    15.75
     progress
    15.69
    证据
    15.63
    ature
    15.56
    Activations Density 0.158%

    No Known Activations