© 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. 29435
    Prev
    Next
    INDEX
    Explanations

    academic texts, scientific papers

    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
    å¦ĤæŀľæĪij们
    -0.09
    æĬ¥åijĬ
    -0.09
    使æĪij
    -0.09
    çłĶ究æĬ¥åijĬ
    -0.08
    æĬ¥åijĬæĺ¾ç¤º
    -0.08
    让æĪij
    -0.08
    pch
    -0.08
     ÑĤоÑĤ
    -0.08
    人åıĤ
    -0.08
    æIJ
    -0.08
    POSITIVE LOGITS
    lington
    0.09
    å´§
    0.09
    æ¸ħåįİ
    0.09
    æķ¬ä¸ļ
    0.09
    ynet
    0.09
    ãĤ«ãĥ«
    0.09
    æŀIJ
    0.08
    iete
    0.08
    ç½ijæ°ij
    0.08
     PaÅĦst
    0.08
    Activations Density 0.051%

    No Known Activations