© 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. 2021
    Prev
    Next
    INDEX
    Explanations

    Muslim

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

    No Comments

    Negative Logits
     Muslim
    -55.75
    Muslim
    -50.25
     Muslims
    -50.25
    穆
    -50.00
     Mus
    -44.75
     mus
    -44.00
     muslim
    -43.75
    µ
    -43.75
    Mus
    -43.75
     µ
    -43.00
    POSITIVE LOGITS
    秦皇岛
    17.13
    金
    15.81
    Gold
    15.81
    雪花
    15.75
    药
    15.69
    黄金
    15.69
    SOFTWARE
    15.56
     Pharmac
    15.44
    (arc
    15.44
    锗
    15.31
    Activations Density 0.043%

    No Known Activations