© 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. 57369
    Prev
    Next
    INDEX
    Explanations

    minor league sports organizations

    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
    ä¼Ĭæĸ¯
    -0.09
    æ²īæµ¸åľ¨
    -0.09
    åı¯éĿłçļĦ
    -0.09
    ä¸įçIJĨ
    -0.08
    没éĹ®é¢ĺ
    -0.08
    ego
    -0.08
    æĸ°æĪ¿
    -0.08
    åij¨åĽ´çļĦ
    -0.08
    æīĢåľ¨çļĦ
    -0.08
    å¸ļ
    -0.08
    POSITIVE LOGITS
    sts
    0.10
    arth
    0.09
    æ±ľ
    0.09
     Hutchinson
    0.09
    设æĸ½å»ºè®¾
    0.08
    éĨ¯
    0.08
     Bulletin
    0.08
    举é£İ
    0.08
    é¾ĻéŨ
    0.08
    缯
    0.08
    Activations Density 0.012%

    No Known Activations