© 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. 63859
    Prev
    Next
    INDEX
    Explanations

    challenge and meme

    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
    yne
    -0.10
    央
    -0.10
     Españ
    -0.09
    奶
    -0.09
    Ñģи
    -0.08
    .dimension
    -0.08
    qus
    -0.08
     пÑģ
    -0.08
    Facing
    -0.08
    ä¸Ģç«Ļå¼ı
    -0.08
    POSITIVE LOGITS
    ç»ĵæĿŁåIJİ
    0.10
    è¿ĩåIJİ
    0.10
    ÑĪи
    0.09
    å¾Ĺ罪
    0.09
    è§Ħå®ļçļĦ
    0.09
    管çIJĨåĬŀæ³ķ
    0.09
    çļĦ缮çļĦ
    0.08
    æľĪ以æĿ¥
    0.08
    çļĦè¦ģæ±Ĥ
    0.08
    ponsored
    0.08
    Activations Density 0.064%

    No Known Activations