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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15154
    Prev
    Next
    INDEX
    Explanations

    royalty

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

    No Comments

    Negative Logits
    крут
    -19.63
    圩
    -18.63
    獠
    -18.50
    机动
    -17.50
    结构调整
    -16.88
    蚓
    -16.63
    warts
    -16.25
    mlink
    -16.13
    蠡
    -15.94
    髑
    -15.88
    POSITIVE LOGITS
     royal
    24.88
    皇后
    23.88
    帝王
    23.00
    皇子
    22.88
     Majesty
    22.63
    皇家
    22.38
    皇帝
    22.38
    朕
    21.50
     queen
    21.38
     Queen
    20.88
    Activations Density 0.212%

    No Known Activations