© 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. 2236
    Prev
    Next
    INDEX
    Explanations

    say "embed"

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

    No Comments

    Negative Logits
    氧
    -19.13
    饮
    -19.13
    .Chat
    -18.00
    舔
    -17.63
    SDL
    -17.50
    (passport
    -17.50
     Oxygen
    -17.50
    Tp
    -17.25
    (pm
    -17.13
    饮品
    -16.88
    POSITIVE LOGITS
     fract
    24.13
     embedding
    18.00
     Floyd
    17.75
    嵌
    17.13
    MBED
    16.25
     embedded
    16.00
    embedding
    16.00
     embeddings
    15.88
    Embed
    15.31
     gö
    15.31
    Activations Density 0.045%

    No Known Activations