© 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. 2699
    Prev
    Next
    INDEX
    Explanations

    say "育"

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

    No Comments

    Negative Logits
    reflection
    -20.13
    mirror
    -19.38
    镜子
    -18.88
     Reflection
    -18.25
     quant
    -17.88
    dict
    -17.75
     reflection
    -17.25
     mirror
    -17.13
    Reflection
    -17.00
    Dict
    -16.75
    POSITIVE LOGITS
    育
    48.00
    (ret
    22.00
    培育
    21.88
    Ret
    21.25
    ret
    20.13
     Ret
    19.50
    .Ret
    19.38
     genotype
    18.88
    _ret
    18.25
    _RET
    18.25
    Activations Density 0.060%

    No Known Activations