© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 194
    Prev
    Next
    INDEX
    Explanations

    say "TO"

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

    No Comments

    Negative Logits
    INA
    -20.00
     INA
    -19.50
     FB
    -19.50
    佛法
    -19.50
    袈
    -19.50
    佛
    -19.50
    佛教
    -19.50
    JB
    -19.38
     Oracle
    -19.38
    %@
    -19.13
    POSITIVE LOGITS
     TO
    26.63
    .TO
    26.50
    TO
    25.88
     Toledo
    25.50
    太原
    23.75
     Denver
    22.88
     Toronto
    22.75
    天津市
    21.13
     Tf
    21.00
    _tf
    20.75
    Activations Density 0.542%

    No Known Activations