© 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. 33973
    Prev
    Next
    INDEX
    Explanations

    taxable income and expenses

    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
    ĥģ
    -0.07
    è£ķ
    -0.07
    cad
    -0.06
     ÑħÑĢан
    -0.06
    ums
    -0.06
    建æĪIJåIJİ
    -0.06
    ØŃÙĥاÙħ
    -0.06
    tol
    -0.06
    uy
    -0.06
    ffy
    -0.06
    POSITIVE LOGITS
    æıIJæĹ©
    0.09
    æĻ®æŀĹ
    0.08
    æįŁçĽĬ
    0.08
    eselect
    0.08
    主èIJ¥ä¸ļåĬ¡
    0.07
    æĶ¶åħ¥
    0.07
    oen
    0.07
    主èIJ¥ä¸ļåĬ¡æĶ¶åħ¥
    0.07
    Income
    0.07
    indak
    0.07
    Activations Density 0.012%

    No Known Activations