© 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. 1543
    Prev
    Next
    INDEX
    Explanations

    [电气] => [电气]

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

    No Comments

    Negative Logits
    电气
    -44.00
     electrical
    -41.50
     Electrical
    -39.25
    电器
    -29.25
     electric
    -28.88
     électrique
    -27.38
     Electric
    -26.63
    electric
    -26.38
    Electric
    -25.13
    Elect
    -24.63
    POSITIVE LOGITS
    MATRIX
    16.38
     matrix
    15.56
     YT
    14.88
     Pond
    14.81
    -mounted
    14.81
    altimore
    14.69
     garden
    14.69
     Chicago
    14.63
     GetHashCode
    14.50
     sound
    14.44
    Activations Density 0.035%

    No Known Activations