© 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. 30090
    Prev
    Next
    INDEX
    Explanations

    drug names and manufacturers

    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
    icorn
    -0.11
    iren
    -0.10
     ÙħÙĩÙħ
    -0.10
     оÑĤкÑĢÑĭва
    -0.09
    æľī趣
    -0.09
    дей
    -0.09
    SSION
    -0.09
     nguyá»ĩn
    -0.09
    æĸ¹éĴĪ
    -0.09
    æħ¢æħ¢çļĦ
    -0.09
    POSITIVE LOGITS
    æ¶īå«Į
    0.11
    ä¸įåIJĪæł¼
    0.09
    使çĶ¨çļĦ
    0.09
    åı¯èĥ½åŃĺåľ¨
    0.09
    æī¹æ¬¡
    0.09
    å¾Īæľīåı¯èĥ½
    0.09
    åIJ«æľī
    0.08
    æľªç»ıæİĪæĿĥ
    0.08
    åıĹåĪ°å½±åĵį
    0.08
    åľ¨åħ¶
    0.08
    Activations Density 0.054%

    No Known Activations