© 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. 586
    Prev
    Next
    INDEX
    Explanations

    say "mythology"

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

    No Comments

    Negative Logits
     Rabbi
    -20.13
     Mahmoud
    -20.00
     الشيخ
    -19.75
     Kuwait
    -19.63
    eken
    -19.25
     Lahore
    -19.25
    中东
    -18.75
     Palestinian
    -18.25
     mosques
    -18.25
     Beirut
    -18.00
    POSITIVE LOGITS
    神话
    20.88
     mortal
    15.50
     Dragon
    15.50
    psilon
    15.44
     Pandora
    15.25
     Titans
    15.06
     Olympia
    15.00
    娥
    15.00
     dragon
    14.81
     Hercules
    14.69
    Activations Density 0.144%

    No Known Activations