© 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. 685
    Prev
    Next
    INDEX
    Explanations

    "And you" or "Do you"

    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
    èĦijæµ·ä¸Ń
    -0.09
    åıĪä¸Ģ次
    -0.09
    IONS
    -0.09
    è¯Ģ
    -0.09
    ç¼ķ
    -0.08
    足以
    -0.08
    è¿Ļä¸įæĺ¯
    -0.08
    ICY
    -0.08
    ihan
    -0.08
    èķ
    -0.08
    POSITIVE LOGITS
    èĭ£
    0.09
    stä
    0.08
    åĴª
    0.08
    Telegram
    0.08
    Ñĩин
    0.08
     ÐľÐ¾Ñģков
    0.08
    éĿĴ
    0.08
    аÑĩ
    0.08
    人ãģ®
    0.08
     nieu
    0.07
    Activations Density 0.079%

    No Known Activations