© 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. 761
    Prev
    Next
    INDEX
    Explanations

    say Buddhist words

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

    No Comments

    Negative Logits
    脚
    -18.25
    olina
    -17.38
    缙
    -16.88
    腳
    -16.50
     FS
    -16.38
    (recipe
    -16.38
    (ic
    -16.00
    ╛
    -16.00
     nc
    -15.94
    ಚ
    -15.63
    POSITIVE LOGITS
     Buddhist
    42.50
     Buddhism
    39.25
     Buddh
    37.50
    佛教
    37.00
     Buddha
    33.50
     Oracle
    30.00
    Oracle
    28.63
     Phật
    27.88
     budd
    27.75
     <?=
    26.38
    Activations Density 0.051%

    No Known Activations