© 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. 24110
    Prev
    Next
    INDEX
    Explanations

    hormone therapy and contraception

    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¨Ģ
    -0.09
    湫
    -0.08
    çĦ¯
    -0.08
    æŀľæłij
    -0.08
    å¯Łçľĭ
    -0.08
    æĸ«
    -0.08
    å¤ļæĸ¹
    -0.08
    ä¸İä¼Ĺ
    -0.08
    aso
    -0.08
    å®ŀä¹ł
    -0.08
    POSITIVE LOGITS
    .mas
    0.10
    nette
    0.10
     conting
    0.09
    å®īåħ¨äºĭæķħ
    0.09
    èĥ¡åŃIJ
    0.09
    inton
    0.09
    LP
    0.09
    floating
    0.09
    _rsp
    0.09
    ç´ł
    0.09
    Activations Density 0.176%

    No Known Activations