© 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
    2. Qwen3-1.7B
    3. 26-LLAMASCOPE-2-LORSA-16K-K64
    4. 373
    Prev
    Next
    INDEX
    Explanations

    say "SE"

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

    No Comments

    Negative Logits
    滏
    -20.00
    酪
    -17.25
    酸奶
    -16.63
    邢台
    -16.63
    赣州
    -16.50
     Hockey
    -16.38
    嘎
    -16.25
    (IT
    -15.88
    OI
    -15.88
     CA
    -15.63
    POSITIVE LOGITS
    SE
    53.00
     SE
    52.75
    (SE
    48.00
     SEA
    40.25
    _SE
    39.75
    SEA
    39.75
    SES
    39.25
     SEL
    37.00
     SES
    37.00
    SEL
    36.75
    Activations Density 0.274%

    No Known Activations