© 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. 23982
    Prev
    Next
    INDEX
    Explanations

    motherhood and pregnancy

    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
    Not in Any Lists

    No Comments

    Negative Logits
    éĴŀ
    -0.10
    å¦ĩ
    -0.09
     matrimon
    -0.09
    éħįåģ¶
    -0.09
     Geli
    -0.08
    æĵĺ
    -0.08
    åĿĩ
    -0.08
    èĭ¹
    -0.08
    éĻª
    -0.08
    æĿľç»Ŀ
    -0.08
    POSITIVE LOGITS
    åŀĦ
    0.12
    olg
    0.10
    缪
    0.09
     Monster
    0.09
    å¾Ĥ
    0.09
    大éĻĨ
    0.09
    伸åĩº
    0.09
    åŀ
    0.09
    åĤ²
    0.09
    Monster
    0.08
    Activations Density 0.107%

    No Known Activations