© 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. 14251
    Prev
    Next
    INDEX
    Explanations

    say push

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

    No Comments

    Negative Logits
     sources
    -22.38
    /sources
    -22.00
     installations
    -21.88
     source
    -21.75
    安装
    -20.63
    	source
    -20.38
    sources
    -20.38
    source
    -20.25
     getSource
    -20.00
     installation
    -19.88
    POSITIVE LOGITS
     Push
    20.63
     push
    19.75
     pushes
    19.63
     pushed
    19.50
     pushing
    19.00
    push
    18.50
    Push
    18.38
    推进
    18.25
    推
    17.88
     PUSH
    15.69
    Activations Density 1.235%

    No Known Activations