© 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. 15489
    Prev
    Next
    INDEX
    Explanations

    say expense words

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

    No Comments

    Negative Logits
    ulia
    -18.13
    璃
    -17.13
    ssql
    -17.00
    自贸区
    -16.50
    inecraft
    -16.50
    IGNAL
    -16.38
    (interp
    -16.13
     Fortress
    -15.75
    _WIN
    -15.63
     Ariel
    -15.63
    POSITIVE LOGITS
    支出
    38.75
    开支
    35.00
     expenditure
    34.75
     expense
    33.50
     expenses
    33.25
    expense
    33.25
     expenditures
    33.00
     Expense
    32.75
     spending
    31.13
    expenses
    30.25
    Activations Density 0.173%

    No Known Activations