© 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. 16637
    Prev
    Next
    INDEX
    Explanations

    medical and scientific contexts

    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
    åħ¶ä¸Ńä¹ĭä¸Ģ
    -0.10
    alc
    -0.09
    衾
    -0.09
     Barry
    -0.09
    å¯Įæ°ij
    -0.09
     **)
    -0.09
    å¾Īæ¼Ĥ亮
    -0.09
    å¤ĩåıĹ
    -0.08
    éĿŀ常å¤ļçļĦ
    -0.08
    [loc
    -0.08
    POSITIVE LOGITS
    .newaxis
    0.11
    æݥ触åĪ°
    0.09
    hread
    0.09
    æĥħåĨµæĿ¥çľĭ
    0.09
    ä¸Ģä½ĵ
    0.09
    -ahead
    0.08
    ÙĨÙĬÙĨ
    0.08
    !]
    0.08
    æł¹åºķ
    0.08
    ä¸Ģå¼Ģå§ĭ
    0.08
    Activations Density 0.695%

    No Known Activations