© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1854
    Prev
    Next
    INDEX
    Explanations

    [兵] => [家]

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

    No Comments

    Negative Logits
    兵
    -34.75
    衣
    -19.13
     css
    -18.50
     socket
    -18.00
     WORD
    -17.88
    (css
    -17.63
     Socket
    -17.13
    軍
    -17.00
    (socket
    -16.88
     Turkish
    -16.75
    POSITIVE LOGITS
    google
    20.63
    -google
    20.00
    Google
    18.88
    燃料
    18.75
     Google
    18.50
     google
    18.00
     mitochondrial
    17.75
    xBE
    16.63
    燃料电池
    16.13
     polynomial
    16.00
    Activations Density 0.101%

    No Known Activations