© 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. 16320
    Prev
    Next
    INDEX
    Explanations

    say "2"

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

    No Comments

    Negative Logits
    三分之一
    -19.63
    .snap
    -17.63
     thirteen
    -17.00
    三期
    -16.25
    １
    -16.00
     Stephens
    -16.00
    第三个
    -15.94
     slips
    -15.88
     snapping
    -15.75
     slipping
    -15.69
    POSITIVE LOGITS
    orable
    18.13
     chol
    17.50
     McKenzie
    17.13
     Maul
    16.25
    (ins
    16.13
    ilm
    15.69
    iken
    15.56
    reur
    15.31
     brew
    15.31
     Brewers
    15.25
    Activations Density 0.032%

    No Known Activations