© 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. 2888
    Prev
    Next
    INDEX
    Explanations

    religion

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

    No Comments

    Negative Logits
    贵阳
    -20.38
    锰
    -20.13
    池
    -19.00
     Buenos
    -18.75
    厨师
    -18.13
    黔
    -18.00
    天然气
    -17.75
    阿根廷
    -17.50
    售后
    -17.38
     Chef
    -17.25
    POSITIVE LOGITS
    宗教
    34.25
     religions
    30.75
    ศาสนา
    30.63
     Christianity
    30.50
    基督教
    30.25
    佛教
    30.00
     religion
    29.88
     religious
    29.13
     atheist
    29.13
    信徒
    28.63
    Activations Density 0.356%

    No Known Activations