© 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. 16628
    Prev
    Next
    INDEX
    Explanations

    gratitude and thankfulness

    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
     Abr
    -0.09
    Ñģад
    -0.09
    etto
    -0.08
     Guarantee
    -0.08
    ä¸įå®ļ
    -0.08
    હ
    -0.08
     easing
    -0.08
     courage
    -0.08
    æ¯Ľ
    -0.08
     wÅĤ
    -0.08
    POSITIVE LOGITS
    æĦŁæģ©
    0.17
    æĦŁæ¿Ģ
    0.14
    çıįæĥľ
    0.12
    æĦŁè¬Ŀ
    0.12
     thankful
    0.11
     grateful
    0.11
     Thanksgiving
    0.11
     благодаÑĢ
    0.11
    æĦŁè°¢
    0.11
     gratitude
    0.11
    Activations Density 0.040%

    No Known Activations