© 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. 62228
    Prev
    Next
    INDEX
    Explanations

    questions and 'do you'

    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
    纪å¾ĭ
    -0.09
    为客æĪ·
    -0.09
    OURS
    -0.08
    èĢģ人家
    -0.08
    è²Į
    -0.08
    iveau
    -0.08
    è¹Ļ
    -0.08
    ä¸įæĺİçĻ½
    -0.08
    ç½¢äºĨ
    -0.08
    çħŀ
    -0.08
    POSITIVE LOGITS
    äºĨ解ä¸Ģä¸ĭ
    0.11
    è¿ĽåŁİ
    0.09
    ÑģÑħод
    0.09
    alo
    0.09
    æľīæĦı
    0.08
    æĪijéĥ½
    0.08
    å±ĬæŶ
    0.08
     GPLv
    0.08
     ste
    0.08
    ãĥķãĥªãĥ¼
    0.08
    Activations Density 0.084%

    No Known Activations