© 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. 8024
    Prev
    Next
    INDEX
    Explanations

    classification and decision-making tasks

    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
    åĽĬ
    -0.10
    åĦ¿å¥³
    -0.09
    梦
    -0.09
    å°ĺ
    -0.09
    åĴĮåıijå±ķ
    -0.09
    å®ı
    -0.09
    交ä¼ļ
    -0.08
    å¾·å°Ķ
    -0.08
     fri
    -0.08
    éĿ¡
    -0.08
    POSITIVE LOGITS
    åIJĥå®Į
    0.10
    æĥħå¢ĥ
    0.09
    西æ´ĭ
    0.09
    ä¸Ģå¦ĤæĹ¢å¾Ģ
    0.09
    å®ŀéªĮ
    0.09
    好åIJĥ
    0.08
    rimp
    0.08
    çī©åĵģ
    0.08
    å·¥åķĨå±Ģ
    0.08
    ìĨį
    0.08
    Activations Density 0.396%

    No Known Activations