© 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. 1574
    Prev
    Next
    INDEX
    Explanations

    say "finance nouns"

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

    No Comments

    Negative Logits
     TAX
    -44.25
     tax
    -43.75
     taxes
    -43.75
    Tax
    -42.50
     Tax
    -42.25
    税收
    -42.00
    _tax
    -41.50
    税
    -41.00
     taxation
    -39.75
     Taxes
    -39.75
    POSITIVE LOGITS
    icho
    16.63
    第一书记
    15.44
    镈
    15.38
    SDL
    14.19
    icc
    13.75
    鲩
    13.56
    偃
    13.50
     circuits
    13.44
    珠三角
    13.44
     Miami
    13.38
    Activations Density 0.108%

    No Known Activations