© 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. 16347
    Prev
    Next
    INDEX
    Explanations

    say names

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

    No Comments

    Negative Logits
    (sw
    -30.50
    _sw
    -29.50
     Swift
    -28.25
    swagger
    -26.38
    Swift
    -26.25
    	sw
    -26.25
    dart
    -26.00
     swipe
    -26.00
    -sw
    -26.00
     Swipe
    -25.75
    POSITIVE LOGITS
     Evel
    21.25
    oko
    20.00
     Cheryl
    19.25
    eko
    19.00
     Pasta
    18.63
     Nicol
    18.50
     Neh
    17.88
     Carol
    17.50
     Monica
    17.25
     Zimmerman
    17.13
    Activations Density 6.914%

    No Known Activations