© 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. 49922
    Prev
    Next
    INDEX
    Explanations

    children's medical studies

    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
    累累
    -0.09
    åĽĬ
    -0.09
    天ä¸ĭ
    -0.08
    æĪIJåijĺåĽ½
    -0.08
    iew
    -0.08
    lah
    -0.08
    odor
    -0.08
    å¨ĺå¨ĺ
    -0.08
    对åѦçĶŁ
    -0.08
    æ£ļ
    -0.08
    POSITIVE LOGITS
    ä¸ŃåŃĺåľ¨çļĦ
    0.10
    大éĻĨ
    0.09
    åľ¨æİ¥åıĹ
    0.09
    身ä¸Ĭ
    0.09
    åľ¨ä»ĸçļĦ
    0.09
    åı¯æł¹æį®
    0.08
    çļ´
    0.08
    éľ°
    0.08
    çħ³
    0.08
    -middle
    0.08
    Activations Density 0.264%

    No Known Activations