© 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. 31490
    Prev
    Next
    INDEX
    Explanations

    medical procedures discomfort

    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
     ÙĪاÙĦØ¥
    -0.10
    onna
    -0.09
     architect
    -0.09
    èªŀ
    -0.09
    æ½ľ
    -0.09
    çľĭä¸įåĩº
    -0.09
    /english
    -0.09
    è¯Ń
    -0.08
    æ¶Ľ
    -0.08
    EFAULT
    -0.08
    POSITIVE LOGITS
    æĮĩå°ĸ
    0.12
    æijĬ
    0.11
    æįı
    0.10
    æ£īèĬ±
    0.10
    ä½ĵéªĮ
    0.10
    çĮ®è¡Ģ
    0.10
    åį°ç«ł
    0.10
    æĶ¾åѦ
    0.09
    æľºåĻ¨
    0.09
    å·¥ä½ľäººåijĺ
    0.09
    Activations Density 0.158%

    No Known Activations