© 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. 2898
    Prev
    Next
    INDEX
    Explanations

    say "桃"

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

    No Comments

    Negative Logits
    輪
    -19.25
    Nib
    -16.75
     chorus
    -14.81
     rollers
    -14.75
     khúc
    -14.63
    ombre
    -14.44
     caul
    -14.06
    Segment
    -13.81
    inks
    -13.81
    _BIN
    -13.56
    POSITIVE LOGITS
    桃
    66.00
    桃花
    36.25
     peach
    27.25
    陶
    26.25
    桃園
    26.13
    (tree
    25.63
    树
    24.25
     tree
    24.00
    -tree
    23.50
    杏
    23.50
    Activations Density 0.027%

    No Known Activations