© 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. 678
    Prev
    Next
    INDEX
    Explanations

    Hinduism

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

    No Comments

    Negative Logits
    亳
    -22.75
     MG
    -22.00
    昆明
    -21.88
     Manitoba
    -21.13
     Mong
    -20.75
    滁
    -20.75
     AZ
    -20.63
    云南省
    -20.25
    滇
    -20.25
    MG
    -20.00
    POSITIVE LOGITS
     Hindu
    30.63
     Hindus
    29.00
    宗教
    24.00
    梵
    21.00
     Hof
    20.00
     religious
    19.75
     java
    19.13
     Brah
    18.88
    信徒
    18.50
    	java
    18.25
    Activations Density 0.130%

    No Known Activations