© 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. 40381
    Prev
    Next
    INDEX
    Explanations

    New Year's or day celebration

    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
    hoff
    -0.11
    uish
    -0.10
    çľ·
    -0.09
    çĶŁäº§è®¾å¤ĩ
    -0.09
    nst
    -0.09
    amate
    -0.09
    æĪ¿
    -0.09
    HashCode
    -0.08
    edin
    -0.08
    å¾ħ
    -0.08
    POSITIVE LOGITS
    æģ¯æģ¯
    0.09
    åĹij
    0.09
    鸡汤
    0.08
    tera
    0.08
    _ANT
    0.08
    æĨ¬
    0.08
     коÑĤоÑĢое
    0.08
    äºİæĺ¯æĪij
    0.08
    太æ¹ĸ
    0.08
    ter
    0.08
    Activations Density 0.003%

    No Known Activations