© 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. 18246
    Prev
    Next
    INDEX
    Explanations

    e-commerce or eCommerce

    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
    æĭ¥
    -0.10
    ä¿®åħ»
    -0.09
    çĶľçĶľ
    -0.09
    é¹ĺ
    -0.09
    fern
    -0.09
    VERN
    -0.08
    ä½ĵä¼ļ
    -0.08
     дело
    -0.08
    å¿ĥå¾Ĺ
    -0.08
    amina
    -0.08
    POSITIVE LOGITS
    prestashop
    0.09
    æģIJ
    0.09
    è´µ
    0.09
    ergus
    0.09
    交æĺĵ
    0.09
    åķĨåŁİ
    0.08
    çķĻä½ı
    0.08
    夯å®ŀ
    0.08
     ìĺģ
    0.08
     ITEMS
    0.08
    Activations Density 0.134%

    No Known Activations