© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 738
    Prev
    Next
    INDEX
    Explanations

    say "Genesis"

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

    No Comments

    Negative Logits
    是韩国
    -21.00
     Tamil
    -20.13
    温州
    -20.00
    erox
    -19.50
    BMW
    -19.38
    槟
    -19.13
     tamil
    -19.13
    Battery
    -19.00
     Newport
    -19.00
    杭州
    -18.88
    POSITIVE LOGITS
     Braz
    20.00
     Edmonton
    19.00
     Alberta
    16.63
    Genesis
    16.13
     ranch
    15.25
    秣
    15.06
    冈
    15.06
     Abraham
    14.88
    丕
    14.88
    斧
    14.81
    Activations Density 0.101%

    No Known Activations