© 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. 12193
    Prev
    Next
    INDEX
    Explanations

    consequential damages or effects

    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
    æŀľæłij
    -0.09
    ês
    -0.09
    è¡ĮæĿİ
    -0.09
    gary
    -0.08
    å½¼æѤ
    -0.08
    æĹ¶è¾°
    -0.08
    å°ijåIJĥ
    -0.08
    ç°ª
    -0.08
    uela
    -0.08
     obra
    -0.08
    POSITIVE LOGITS
    ities
    0.09
    æīĭ段
    0.09
    ties
    0.09
    idget
    0.09
    iggers
    0.09
    سÙĪ
    0.08
    Elf
    0.08
    à¸Ļม
    0.08
    ucker
    0.08
    tran
    0.08
    Activations Density 0.006%

    No Known Activations