© 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. 15756
    Prev
    Next
    INDEX
    Explanations

    say "sw" words

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

    No Comments

    Negative Logits
     Evel
    -22.38
     Cheryl
    -20.75
    oko
    -20.63
    eko
    -20.25
     Pasta
    -20.13
     Nicol
    -19.63
     Neh
    -19.00
     Zimmerman
    -18.75
     Carol
    -18.63
    Carol
    -18.63
    POSITIVE LOGITS
    (sw
    29.50
    _sw
    29.38
     Swift
    27.88
    	sw
    25.75
    -sw
    25.75
    Swift
    25.50
    swagger
    25.25
     Sw
    25.25
    _SW
    25.00
     swipe
    24.88
    Activations Density 7.105%

    No Known Activations