© 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. 15658
    Prev
    Next
    INDEX
    Explanations

    say "recursive"

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

    No Comments

    Negative Logits
     Carb
    -20.63
     Sandwich
    -19.50
    -car
    -19.13
     Car
    -18.50
     sushi
    -18.38
    .Car
    -18.25
    汉堡
    -18.13
    (car
    -17.75
     carb
    -17.63
     Hamburg
    -17.50
    POSITIVE LOGITS
    recursive
    18.25
    _recursive
    17.88
     Colin
    17.00
    Recursive
    16.88
     recursively
    16.75
     recursive
    16.50
    CAT
    16.38
    递
    16.38
    cat
    15.94
    .cat
    15.94
    Activations Density 1.112%

    No Known Activations