© 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. 64011
    Prev
    Next
    INDEX
    Explanations

    child, baby, pregnancy, parents

    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
    æ¯ı人
    -0.09
    è½°
    -0.09
    åIJĦè¡Į
    -0.09
    æĤ²åĵĢ
    -0.08
     Garn
    -0.08
    yles
    -0.08
    iero
    -0.08
    åľĨ满å®ĮæĪIJ
    -0.08
    é¢ijç¹ģ
    -0.08
     каж
    -0.08
    POSITIVE LOGITS
    ocy
    0.10
    éħĿéħ¿
    0.09
    æĸ°çļĦ
    0.09
    æī£
    0.08
    æľĢåħĪ
    0.08
    idar
    0.08
    åijĵ
    0.08
    бав
    0.08
    utter
    0.08
    .layouts
    0.08
    Activations Density 0.026%

    No Known Activations