© 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. 29616
    Prev
    Next
    INDEX
    Explanations

    electronic books and formats

    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
    Lite
    -0.11
    广çĶµ
    -0.10
    çļĩ
    -0.09
    大çĪ·
    -0.09
    裨
    -0.09
    åĪĽæĦı
    -0.09
    åħ³ä¹İ
    -0.09
    缺失
    -0.09
    çĪ·
    -0.08
    åĨĴ
    -0.08
    POSITIVE LOGITS
    åħĪè¡Į
    0.08
    å¼Ħå¾Ĺ
    0.08
    trap
    0.08
     CY
    0.08
    é¦ĸåıij
    0.08
    è¾ĵç»Ļ
    0.08
    缼è¡Į
    0.08
    éĺħ读åħ¨æĸĩ
    0.08
    -pdf
    0.08
    çļĦä¼ĺåĬ¿
    0.08
    Activations Density 0.038%

    No Known Activations