© 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. 26054
    Prev
    Next
    INDEX
    Explanations

    etiology and causes

    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
    ç§ijæķĻ
    -0.08
    (sk
    -0.08
    åħ±äº«
    -0.08
    åľ¨ç½ij绾
    -0.08
    .zz
    -0.08
     nhá»Ŀ
    -0.08
    bsite
    -0.07
    (hex
    -0.07
    orate
    -0.07
    gow
    -0.07
    POSITIVE LOGITS
    èĸ°
    0.10
    æľªçŁ¥
    0.10
    åħ¨éĿ¢èIJ½å®ŀ
    0.09
    å¾ģä¿¡
    0.09
    ายà¸Ļ
    0.09
    åī©ä¸ĭ
    0.09
    åī©ä¸ĭçļĦ
    0.09
     оÑģÑĤа
    0.09
    åħħ足çļĦ
    0.09
    ÑĥÑĢ
    0.09
    Activations Density 0.315%

    No Known Activations