© 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. 14119
    Prev
    Next
    INDEX
    Explanations

    say "capture"

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

    No Comments

    Negative Logits
    讀
    -20.63
    读
    -19.63
     training
    -19.25
     reader
    -18.88
     train
    -18.63
    Training
    -18.63
    -training
    -18.25
     reading
    -18.25
    -reader
    -18.13
    培训
    -18.00
    POSITIVE LOGITS
     capture
    20.50
    捕捉
    20.00
    capture
    19.50
     capturing
    19.00
     coefficients
    18.63
     captures
    18.38
    抓
    17.88
    captures
    17.75
     captured
    17.63
    ManagerInterface
    17.63
    Activations Density 1.382%

    No Known Activations