© 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. 2553
    Prev
    Next
    INDEX
    Explanations

    say "percent"

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

    No Comments

    Negative Logits
    Curr
    -21.00
     Specs
    -19.75
    _refs
    -19.50
    Refs
    -19.50
    curr
    -19.38
    Opts
    -19.38
    	ref
    -18.88
     refs
    -18.63
    	args
    -18.50
     curr
    -18.25
    POSITIVE LOGITS
    segment
    21.75
    (segment
    21.13
    Segment
    21.13
    .segment
    20.88
     segment
    19.50
     capital
    19.38
    _segment
    19.25
     tab
    18.38
    tab
    18.25
     segmentation
    17.75
    Activations Density 0.050%

    No Known Activations