© 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. 665
    Prev
    Next
    INDEX
    Explanations

    say witchcraft

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

    No Comments

    Negative Logits
     سعود
    -23.63
    丰田
    -23.50
     Suzuki
    -23.13
     Kobe
    -22.75
     Kuwait
    -22.25
    Saudi
    -22.13
     UAE
    -21.75
     Gundam
    -21.63
     sushi
    -20.75
    迪拜
    -20.75
    POSITIVE LOGITS
     Witch
    24.00
     witch
    23.13
     witches
    21.63
     Salem
    17.63
     tội
    16.63
    巫
    16.25
    缢
    16.13
     Sabbath
    15.88
     Sheriff
    15.75
     Satan
    15.69
    Activations Density 0.039%

    No Known Activations