© 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. 14032
    Prev
    Next
    INDEX
    Explanations

    say "sample"

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

    No Comments

    Negative Logits
     track
    -23.75
    Track
    -22.13
    跟踪
    -22.00
    -track
    -21.25
     tracking
    -21.13
     Track
    -21.13
     tracks
    -21.00
    Tracks
    -20.50
    记录
    -20.00
    track
    -19.88
    POSITIVE LOGITS
    代
    15.88
     sample
    15.31
     sampled
    15.13
     Sample
    15.06
    样品
    14.75
     covering
    14.63
    .sample
    14.50
    umer
    14.44
     ký
    14.38
    翕
    14.31
    Activations Density 1.395%

    No Known Activations