© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14146
    Prev
    Next
    INDEX
    Explanations

    say performance

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

    No Comments

    Negative Logits
    小组
    -19.88
     Group
    -19.38
     group
    -19.00
    GroupId
    -18.88
     Experiment
    -18.88
    集团公司
    -18.75
     GROUP
    -18.63
     groups
    -18.63
     группы
    -18.50
    Groups
    -18.38
    POSITIVE LOGITS
    表演
    17.88
     performance
    17.38
    排放
    16.13
    更新
    16.00
    	inter
    16.00
     更新
    16.00
    Performance
    15.94
     perform
    15.94
     update
    15.94
     performances
    15.56
    Activations Density 2.111%

    No Known Activations