© 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. 663
    Prev
    Next
    INDEX
    Explanations

    say "Islamic terms"

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

    No Comments

    Negative Logits
     Jefferson
    -20.63
    Ford
    -18.38
     Knoxville
    -17.75
    HEN
    -17.50
     Wyoming
    -17.50
     Leah
    -17.38
     Ford
    -17.00
    海棠
    -16.75
    Jeff
    -16.63
    Jackson
    -16.63
    POSITIVE LOGITS
    伊斯兰
    19.88
    阿拉伯
    18.25
    谯
    18.00
    波
    16.88
    伊朗
    16.38
    米兰
    16.25
     mosque
    16.13
    ブラ
    16.13
     jihad
    15.69
    竞技
    15.69
    Activations Density 0.081%

    No Known Activations