© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15807
    Prev
    Next
    INDEX
    Explanations

    say doc

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

    No Comments

    Negative Logits
     TableCell
    -16.75
    TableViewCell
    -16.63
     Tribune
    -16.50
     Winnipeg
    -16.13
    巾
    -16.13
     TABLE
    -15.94
    胭
    -15.88
     Tables
    -15.81
    bra
    -15.81
    frauen
    -15.75
    POSITIVE LOGITS
     doc
    29.13
    Doc
    25.75
    	doc
    25.38
     Doc
    25.00
    doc
    24.88
    文档
    24.50
     docs
    23.75
    -document
    23.75
    _doc
    23.38
    	Document
    23.38
    Activations Density 0.089%

    No Known Activations