© 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. 1964
    Prev
    Next
    INDEX
    Explanations

    say "pdf"

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

    No Comments

    Negative Logits
    马
    -46.50
    馬
    -42.75
    马克思
    -36.00
    内马
    -31.00
     MAR
    -30.38
    玛
    -30.00
     Marxism
    -29.25
    MAR
    -29.00
    马来
    -28.00
     Marx
    -26.63
    POSITIVE LOGITS
    -pdf
    19.00
    pdf
    18.63
    _pdf
    18.25
     pdf
    18.13
    HDR
    16.88
    Pdf
    15.94
     PDF
    14.94
     sdf
    14.88
    /pdf
    14.63
    安全
    14.44
    Activations Density 0.088%

    No Known Activations