© 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. 1488
    Prev
    Next
    INDEX
    Explanations

    [电] => [电]

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

    No Comments

    Negative Logits
    电
    -62.25
    Elect
    -58.00
     electric
    -58.00
     Electric
    -55.50
     electrical
    -55.50
    elect
    -54.00
     Electrical
    -54.00
    Electric
    -53.75
     ELECT
    -53.50
    電
    -53.25
    POSITIVE LOGITS
     Symbols
    15.13
     GP
    14.94
     Fischer
    14.63
    Symbols
    13.50
     symbols
    13.13
     Google
    13.00
     sapi
    13.00
     Mario
    12.94
    ardy
    12.88
     Carlo
    12.50
    Activations Density 0.261%

    No Known Activations