© 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. 2851
    Prev
    Next
    INDEX
    Explanations

    say gem

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

    No Comments

    Negative Logits
    (er
    -18.63
    eras
    -18.38
    Er
    -17.25
    erk
    -17.00
    ereg
    -16.88
     Vec
    -16.88
     regulation
    -16.75
    榔
    -16.50
     er
    -15.88
    erville
    -15.63
    POSITIVE LOGITS
    宝
    87.50
    寶
    72.00
     gem
    48.75
     Gem
    46.50
    Gem
    45.50
     gems
    42.75
    gem
    39.75
    宝石
    39.00
    _gem
    38.75
     diamond
    32.50
    Activations Density 0.059%

    No Known Activations