© 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. 16032
    Prev
    Next
    INDEX
    Explanations

    secretions

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

    No Comments

    Negative Logits
     Roz
    -17.75
    娃娃
    -17.63
    镢
    -17.00
     pz
    -16.75
    .Bundle
    -16.63
    嵘
    -16.50
    kel
    -16.38
    阅读全文
    -16.25
    ritz
    -16.13
    aos
    -16.13
    POSITIVE LOGITS
    液体
    23.88
    液
    23.25
     liquids
    23.13
    分泌
    23.00
     secretion
    22.63
     liquid
    22.25
     lubric
    21.38
    润滑
    20.75
    湿润
    20.63
     secret
    20.25
    Activations Density 0.176%

    No Known Activations