© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 3225
    Prev
    Next
    INDEX
    Explanations

    say "存储"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    module
    -18.00
     module
    -17.50
    STS
    -17.13
    /St
    -17.00
    	module
    -16.88
     Module
    -16.38
    工业园区
    -16.25
    ��
    -16.13
    (module
    -16.13
     Designer
    -16.13
    POSITIVE LOGITS
    存储
    27.88
     computation
    21.38
     student
    19.25
    student
    19.00
     compute
    18.88
     storage
    18.75
     store
    18.63
    文档
    18.63
    (student
    18.13
    (document
    18.00
    Activations Density 0.016%

    No Known Activations