© 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. 11696
    Prev
    Next
    INDEX
    Explanations

    business and finance industry terms

    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
     Interactive
    -0.09
    Interactive
    -0.08
     UM
    -0.08
    æīĵæĸŃ
    -0.08
    èĺijèıĩ
    -0.08
    å¸ĺ
    -0.08
     Melissa
    -0.08
     interactive
    -0.08
    ÐĵÐŀ
    -0.08
    æĪIJåĬŁçİĩ
    -0.08
    POSITIVE LOGITS
    Smarty
    0.09
    åĢ¾åIJ¬
    0.09
    群ä½ĵ
    0.09
    éĢµ
    0.09
    å±±åºĦ
    0.09
    esch
    0.09
    訾
    0.09
    ç»´å¥ĩ
    0.08
    å¨ģ
    0.08
    è¡ĹåĮº
    0.08
    Activations Density 0.002%

    No Known Activations