© 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. 2343
    Prev
    Next
    INDEX
    Explanations

    say "segment"

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

    No Comments

    Negative Logits
    ITTER
    -15.69
     sez
    -14.94
     ballot
    -14.56
    лим
    -14.19
    itten
    -14.13
    _approved
    -14.06
    Curr
    -13.75
    总书记在
    -13.75
     barren
    -13.69
    زن
    -13.63
    POSITIVE LOGITS
    段
    100.00
     segment
    98.50
    segment
    93.50
    Segment
    91.50
     Segment
    90.50
    (segment
    90.50
     segments
    87.50
    _segment
    83.00
    .segment
    82.00
     Seg
    81.00
    Activations Density 0.232%

    No Known Activations