© 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. 1651
    Prev
    Next
    INDEX
    Explanations

    medical students and training

    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
    ç¥ŀå·ŀ
    -0.10
    åIJįå¸Ī
    -0.10
    æľįåĬ¡æľºæŀĦ
    -0.09
    caller
    -0.09
    æĻĸ
    -0.09
    ä¸Ĭå¹´åIJĮæľŁ
    -0.09
     оÑĤз
    -0.09
    enty
    -0.09
    æĪijçĪ¸
    -0.09
    å¸ĪèµĦ
    -0.08
    POSITIVE LOGITS
    åѦçĶŁ
    0.22
    åѸçĶŁ
    0.18
    çļĦåѦçĶŁ
    0.17
     students
    0.17
    åѦçĶŁçļĦ
    0.17
     student
    0.16
    æ¯ķä¸ļçĶŁ
    0.16
     ÑģÑĤÑĥденÑĤ
    0.15
    大åѦçĶŁ
    0.15
    é«ĺä¸ŃçĶŁ
    0.14
    Activations Density 0.123%

    No Known Activations