© 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. 716
    Prev
    Next
    INDEX
    Explanations

    sexual behavior and partners

    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®Ŀ
    -0.10
    ruk
    -0.09
    马æĭī
    -0.09
    妨
    -0.09
    ziel
    -0.09
    ä½ıæĪ·
    -0.09
    èĨ³
    -0.09
    åĸĺ
    -0.09
    agens
    -0.08
    åħ¥éŨ
    -0.08
    POSITIVE LOGITS
     partners
    0.11
    ä¼łæĴŃ
    0.11
    æ³
    0.10
    æĬĹåĩ»
    0.10
    ä¼ł
    0.09
    çĶ·æľĭåıĭ
    0.09
    ä¼´ä¾£
    0.09
     mant
    0.09
    æľĭåıĭ们
    0.09
    æ¤İ
    0.09
    Activations Density 0.235%

    No Known Activations