© 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. 14145
    Prev
    Next
    INDEX
    Explanations

    say track

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

    No Comments

    Negative Logits
     definition
    -19.00
    .Export
    -18.88
    (pdf
    -18.75
     pdf
    -18.63
    pdf
    -18.63
    PDF
    -18.63
    $pdf
    -17.75
     PDF
    -17.50
     grades
    -17.50
    Export
    -17.38
    POSITIVE LOGITS
     tracks
    16.38
     track
    15.38
    track
    14.81
    TRACK
    14.44
    .TODO
    14.25
     Track
    14.06
    _tracks
    13.88
     TRACK
    13.63
    证实
    13.56
    .track
    13.44
    Activations Density 1.770%

    No Known Activations