© 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. 2761
    Prev
    Next
    INDEX
    Explanations

    say "doc" words

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

    No Comments

    Negative Logits
     hexadecimal
    -17.13
    工程建设
    -15.81
    建筑工程
    -14.88
    Meg
    -14.75
     HEX
    -14.38
    工程
    -14.38
     simulations
    -14.19
     Hex
    -14.19
    _HEX
    -13.88
     SIM
    -13.75
    POSITIVE LOGITS
     doc
    87.00
     Doc
    75.50
    doc
    75.50
    (doc
    73.50
    	doc
    71.50
    Doc
    70.00
    _doc
    64.00
     docs
    60.75
    .Doc
    58.25
    -doc
    57.25
    Activations Density 0.080%

    No Known Activations