© 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. 11757
    Prev
    Next
    INDEX
    Explanations

    MAGIC: TECHNOLOGICAL INNOVATION

    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
    é«ĺä¸ŃçĶŁ
    -0.16
    é«ĺä¸Ń
    -0.14
    éĿĴå°ijå¹´
    -0.13
     teenagers
    -0.11
    éĿĴæĺ¥æľŁ
    -0.11
     teenage
    -0.11
    é«ĺä¸ī
    -0.10
     teenager
    -0.10
    é«ĺèĢĥ
    -0.10
     اÙĦشباب
    -0.10
    POSITIVE LOGITS
    大éĺŁ
    0.11
    æĭ¼éŁ³
    0.10
    å¹¼åĦ¿
    0.10
    ç©¿è¡£
    0.09
    è½®
    0.09
    ä¸Ģ年级
    0.09
    å°ıæľĭåıĭ
    0.09
    讲æķħäºĭ
    0.09
    åħŃå¹´
    0.09
    forest
    0.08
    Activations Density 0.093%

    No Known Activations