© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36299
    Prev
    Next
    INDEX
    Explanations

    payroll and wages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olla
    -0.10
    éĶĭ
    -0.09
    isons
    -0.09
    åħ´ä¸ļ
    -0.09
    è§Ĩ
    -0.09
    ientes
    -0.09
    ç»Ī身
    -0.09
    ä¸ĢçĶŁ
    -0.09
    ç»Ŀ
    -0.08
    å£ģ
    -0.08
    POSITIVE LOGITS
    å·¥èµĦ
    0.14
     payroll
    0.13
    工人
    0.11
     wages
    0.11
    èģĮå·¥
    0.11
    çĶ¨å·¥
    0.10
    åĬ³åĬ¨åIJĪåIJĮ
    0.10
    飧
    0.10
    èĸª
    0.10
    weekly
    0.10
    Activations Density 0.067%

    No Known Activations