© 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. 20641
    Prev
    Next
    INDEX
    Explanations

    injury and trauma

    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
    æī§
    -0.10
    æĸ¡
    -0.09
    èIJ½åı¶
    -0.09
    æ²½
    -0.09
    象å¾ģ
    -0.09
    åѦåīį
    -0.08
    èŀį
    -0.08
    ç½¢
    -0.08
     ÑĢаÑģ
    -0.08
    åѦåīįæķĻèĤ²
    -0.08
    POSITIVE LOGITS
    交éĢļäºĭæķħ
    0.11
    åŁİ乡
    0.11
    车祸
    0.10
    èĤĩäºĭ
    0.10
    ä¸Ģéģį
    0.10
     injuries
    0.09
    ä¸ŃåĽ½æ±½è½¦
    0.09
    åħ¨åĽ½
    0.09
    æļ´åĬĽ
    0.09
    æīĵäºĨ
    0.09
    Activations Density 0.268%

    No Known Activations