© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19697
    Prev
    Next
    INDEX
    Explanations

    with French, scenes, complementary

    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
    æī¿æĭħ责任
    -0.10
    perator
    -0.09
    å¾Ĵ
    -0.09
    æł¸å¿ĥåĮº
    -0.09
    å¤ĸåĮħ
    -0.09
    å¤ĸè§Ĥ
    -0.09
    æĺİæĺİ
    -0.09
    èĬľ
    -0.09
    人士
    -0.08
    æľī幸
    -0.08
    POSITIVE LOGITS
    åIJĪéĢĤçļĦ
    0.10
    éĢĤåIJĪ
    0.10
    æĦıåij³
    0.09
    æĬĢæľ¯åĴĮ
    0.09
     biên
    0.08
    äºĨä¸Ģ个
    0.08
    agens
    0.08
    äºĨä¸įå°ij
    0.08
    类似
    0.08
    æŀģ为
    0.08
    Activations Density 0.071%

    No Known Activations