© 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. 1858
    Prev
    Next
    INDEX
    Explanations

    [资产] => [阶级]

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

    No Comments

    Negative Logits
     asset
    -35.75
    资产
    -34.00
     Asset
    -33.25
    Asset
    -31.63
     assets
    -29.88
    _asset
    -29.88
    .asset
    -29.13
    资产管理
    -28.88
     Assets
    -28.75
    (asset
    -28.75
    POSITIVE LOGITS
     Di
    22.50
    Di
    20.63
    数学
    20.00
     Ди
    18.63
    math
    18.38
     Mathematics
    18.25
    Math
    17.75
    python
    17.50
     math
    17.13
    _math
    16.63
    Activations Density 0.097%

    No Known Activations