© 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. 973
    Prev
    Next
    INDEX
    Explanations

    say religious

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

    No Comments

    Negative Logits
     Bulgarian
    -25.88
    埃及
    -24.13
    郴州
    -22.00
     Belgian
    -21.63
     Kosovo
    -21.38
    氪
    -21.38
     Morocco
    -21.00
     Luxembourg
    -20.88
    硇
    -20.63
     Belarus
    -20.50
    POSITIVE LOGITS
     Shi
    18.75
     Faith
    16.38
    教
    16.25
    _mi
    16.25
     San
    16.13
     الإمام
    15.56
    的教学
    15.25
     xi
    15.00
    sti
    15.00
    眉
    14.81
    Activations Density 0.103%

    No Known Activations