© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 471
    Prev
    Next
    INDEX
    Explanations

    say Excel

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

    No Comments

    Negative Logits
    粒子
    -21.50
    修士
    -20.50
     particle
    -19.75
    /socket
    -19.75
    /ns
    -19.50
    _wheel
    -19.13
    素食
    -19.13
    particle
    -19.13
    废气
    -19.13
     Napoli
    -19.00
    POSITIVE LOGITS
     Excel
    35.50
    Excel
    34.75
     excel
    30.38
    excel
    29.38
    .Excel
    28.75
    .xlsx
    27.00
    .xls
    24.75
    _excel
    24.13
     Microsoft
    23.25
     cell
    23.00
    Activations Density 0.102%

    No Known Activations