© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10698
    Prev
    Next
    INDEX
    Explanations

    business, organization, financial

    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
    æıĨ
    -0.11
    渤
    -0.10
    (HttpContext
    -0.09
    踵
    -0.09
    ãģ¨ãģª
    -0.09
    aman
    -0.09
    åľ¨èģĮ
    -0.09
    åĬ¨çĶŁæĪIJ
    -0.09
    çľ·
    -0.09
    omal
    -0.08
    POSITIVE LOGITS
    ä¸ļ绩
    0.09
    墩
    0.09
    åĩºèī²çļĦ
    0.09
    æĪĺ绩
    0.08
    績
    0.08
     salvage
    0.08
    LING
    0.08
     vale
    0.08
    åĩºèī²
    0.08
    adel
    0.08
    Activations Density 0.075%

    No Known Activations