© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8098
    Prev
    Next
    INDEX
    Explanations

    family, siblings, dynasties, names

    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
    åijĺ
    -0.11
    ä¿®çĤ¼
    -0.09
    åĵ¡
    -0.09
    æ£Ģå¯Łå®ĺ
    -0.09
    åĭŁ
    -0.09
    åħ¬åĬŀ
    -0.09
    æĪijåĴĮ
    -0.09
    çļĦ对象
    -0.09
    åħ¶ä»ĸåĽ½å®¶
    -0.09
     subsidi
    -0.08
    POSITIVE LOGITS
     family
    0.13
    家æĹı
    0.12
    们
    0.11
    ses
    0.10
     Family
    0.10
    -family
    0.09
    family
    0.09
    çİĭæľĿ
    0.09
    åĢij
    0.09
    æ°ı
    0.09
    Activations Density 0.045%

    No Known Activations