© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1792
    Prev
    Next
    INDEX
    Explanations

    say "Islamic"

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

    No Comments

    Negative Logits
     liver
    -48.50
     Liver
    -48.25
    Liver
    -46.00
    肝脏
    -45.75
    肝
    -44.50
     hepat
    -32.75
     hep
    -30.63
     Hep
    -30.63
     hepatitis
    -25.00
     letters
    -24.00
    POSITIVE LOGITS
    伊斯兰
    24.00
     Muslim
    20.13
     Islamic
    18.88
    .Designer
    18.00
     Muslims
    17.75
    Muslim
    17.50
     المسلمين
    16.00
     Palestinians
    15.56
    Islamic
    15.25
     Islam
    15.00
    Activations Density 0.097%

    No Known Activations