© 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. 1413
    Prev
    Next
    INDEX
    Explanations

    do not say Islamic

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

    No Comments

    Negative Logits
    伊斯兰
    -43.25
     Muslim
    -40.50
     Islam
    -40.00
     Islamic
    -40.00
     Muslims
    -39.25
     muslim
    -35.50
     Islamist
    -34.75
     mosques
    -34.25
    Islam
    -34.00
    Muslim
    -33.75
    POSITIVE LOGITS
    鱼类
    19.13
    钓
    17.00
    金属
    16.63
     computational
    15.75
    渔业
    15.56
    RY
    15.50
    肝脏
    15.38
    fish
    15.19
     matrix
    14.88
     Sound
    14.63
    Activations Density 0.338%

    No Known Activations