© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 58800
    Prev
    Next
    INDEX
    Explanations

    income, wages, property income

    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
    rams
    -0.08
    klam
    -0.08
     Cul
    -0.08
    没æľī帮åĬ©
    -0.07
    jam
    -0.07
    éļ
    -0.07
    ĽĦ
    -0.07
    allet
    -0.07
    alez
    -0.07
    agal
    -0.07
    POSITIVE LOGITS
    åĪĨéħį
    0.10
    æĶ¶åħ¥
    0.09
     income
    0.08
    éĿŀåħ¬æľīåĪ¶
    0.08
    åĪĨéħįçļĦ
    0.08
    çļĦæĶ¶åħ¥
    0.08
     distrib
    0.08
    ä¸Ńä»ĭ
    0.07
    å¤ļåħĥåĮĸçļĦ
    0.07
    çļĦ主导
    0.07
    Activations Density 0.001%

    No Known Activations