© 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. 604
    Prev
    Next
    INDEX
    Explanations

    say "佛教"

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

    No Comments

    Negative Logits
     McMaster
    -19.25
    锰
    -19.13
    郾
    -18.75
    Toronto
    -18.13
    吉林省
    -17.63
    赣
    -17.63
    洈
    -17.38
    YC
    -17.25
    南阳
    -17.25
     Ukr
    -16.38
    POSITIVE LOGITS
    佛
    59.25
    佛教
    48.25
     Java
    43.00
    Java
    41.75
     java
    41.75
    佛法
    41.00
    java
    40.25
     Phật
    40.00
    (java
    39.25
     Buddhist
    39.00
    Activations Density 0.088%

    No Known Activations