© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 64496
    Prev
    Next
    INDEX
    Explanations

    income and taxes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    μαÏĦο
    -0.08
    èĢģäºĮ
    -0.07
    èĢĹæŶ
    -0.07
    åħĮ
    -0.07
    idi
    -0.07
    گار
    -0.07
     backstage
    -0.06
    agy
    -0.06
     rugi
    -0.06
    æ¥ŀ
    -0.06
    POSITIVE LOGITS
     income
    0.10
     incomes
    0.09
    -income
    0.09
    Income
    0.08
    income
    0.08
     adjusted
    0.08
     monthly
    0.08
     federal
    0.08
    Adjusted
    0.08
     household
    0.08
    Activations Density 0.061%

    No Known Activations