© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 59426
    Prev
    Next
    INDEX
    Explanations

    Chinese company names

    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
    Negative Logits
    _PATCH
    -0.09
    sut
    -0.09
    æµģè¡Į
    -0.09
    æĢı
    -0.09
    åľŁè±ª
    -0.08
    åŁİåĮº
    -0.08
    并åıij
    -0.08
    äºĮæīĭæĪ¿
    -0.08
    åĨįæĿ¥
    -0.08
    æĮ¨
    -0.08
    POSITIVE LOGITS
    èĤ¡ä¸ľå¤§ä¼ļ
    0.12
    æµ·å¤ĸ
    0.12
    æĬ«éľ²
    0.11
    çĭ¬ç«ĭèij£äºĭ
    0.10
    èij£äºĭä¼ļ
    0.10
    åħ¬åijĬ称
    0.10
    大èĤ¡ä¸ľ
    0.10
    èij£äºĭ
    0.10
    å¹´æĬ¥
    0.10
    æݧèĤ¡
    0.09
    Activations Density 0.122%

    No Known Activations