© 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. 2779
    Prev
    Next
    INDEX
    Explanations

    say "特"

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

    No Comments

    Negative Logits
    [arr
    -17.50
    安排
    -16.25
     arrange
    -16.25
     arr
    -16.00
     arranging
    -15.69
    arr
    -15.44
    ,idx
    -15.38
     arranged
    -15.38
    idx
    -15.25
    [idx
    -15.13
    POSITIVE LOGITS
    特
    75.50
     Spec
    41.75
     spec
    40.50
    spec
    39.25
    特性
    38.75
    Spec
    37.25
    (spec
    35.25
     special
    34.25
     Special
    33.00
    	spec
    32.75
    Activations Density 0.120%

    No Known Activations