© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    4. 16239
    Prev
    Next
    INDEX
    Explanations

    say "history"

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

    No Comments

    Negative Logits
    .program
    -18.00
    .Component
    -17.38
    阙
    -17.00
     Ø
    -16.38
    transforms
    -16.25
    评定
    -15.94
    定量
    -15.88
     exterior
    -15.81
    评测
    -15.81
    uí
    -15.63
    POSITIVE LOGITS
    土豪
    20.88
    史上
    18.63
    ODO
    18.25
    history
    16.63
    的政治
    16.50
    搞笑
    16.50
    野心
    16.50
    史
    16.25
     history
    16.13
    婊
    15.94
    Activations Density 0.544%

    No Known Activations