© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8020
    Prev
    Next
    INDEX
    Explanations

    diagnosis and medical exam results

    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
    оÑĩнÑĭй
    -0.09
    adh
    -0.08
    åĽŀ头
    -0.08
    egie
    -0.08
    ä¸ĢåľĪ
    -0.08
     naw
    -0.08
    erson
    -0.08
    igmat
    -0.08
    æ²®
    -0.08
    æ´Ĺ
    -0.08
    POSITIVE LOGITS
    æĹ¢è¦ģ
    0.10
    积æŀģéħįåIJĪ
    0.10
    çĸijä¼¼
    0.09
    æķķ
    0.09
    éĴĪ对
    0.09
    æĶĺ
    0.08
    çij¶
    0.08
    å¨ĺ
    0.08
    ä¼łçľŁ
    0.08
    èĮ´
    0.08
    Activations Density 0.052%

    No Known Activations