© 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
    2. Qwen3-1.7B
    3. 26-LLAMASCOPE-2-LORSA-16K-K64
    4. 2621
    Prev
    Next
    INDEX
    Explanations

    say "构成"

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

    No Comments

    Negative Logits
     gettext
    -16.63
     NET
    -16.25
    NET
    -15.63
    .sys
    -15.56
    etched
    -15.13
    乙方
    -15.06
    甲方
    -15.06
    ETCH
    -15.00
     net
    -15.00
    kest
    -14.88
    POSITIVE LOGITS
    构
    46.75
    构成
    45.25
    構
    40.00
     constit
    29.88
    Construct
    29.63
     constitute
    29.13
     constitution
    29.00
    构成了
    28.88
     Construct
    28.63
    construct
    28.13
    Activations Density 0.122%

    No Known Activations