© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 920
    Prev
    Next
    INDEX
    Explanations

    Augustine

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

    No Comments

    Negative Logits
     CLR
    -21.50
     CD
    -21.38
     Rahman
    -20.88
     Hindi
    -19.88
     CF
    -19.75
     Kurdish
    -19.75
    CD
    -19.63
     Mah
    -19.38
     Bollywood
    -19.38
     Raj
    -19.13
    POSITIVE LOGITS
     Augustine
    30.00
     Augusta
    29.13
     AUG
    22.88
     Savannah
    22.38
    Austin
    21.25
     Austin
    21.25
     AIS
    20.38
     SG
    20.25
     Utah
    20.25
    SG
    20.25
    Activations Density 0.105%

    No Known Activations