© 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. 56660
    Prev
    Next
    INDEX
    Explanations

    his career, his injury, his season

    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
     ÄijÃŃch
    -0.09
    éĤ£ä¸ªæŶåĢĻ
    -0.09
     اÙĦسÙĬ
    -0.09
    rone
    -0.09
    绪
    -0.09
    iani
    -0.09
    éĤ£æŶ
    -0.09
     thất
    -0.09
     Giấy
    -0.08
    chten
    -0.08
    POSITIVE LOGITS
    累计
    0.10
    å¿ĥå¢ĥ
    0.08
    æĤĴ
    0.08
    acity
    0.08
    为äºĨ让
    0.08
    åıªæľīä¸Ģ个
    0.08
    大åѦæ¯ķä¸ļ
    0.08
    çĶŁæķĪ
    0.08
    ä½ıäºĨ
    0.08
    ä¿¡æģ¯ç³»ç»Ł
    0.08
    Activations Density 0.030%

    No Known Activations