© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 33880
    Prev
    Next
    INDEX
    Explanations

    pregnant or 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
     Aster
    -0.09
    èĩªåįij
    -0.09
    ç»ĿæľĽ
    -0.09
    ç´§å¼ł
    -0.09
    urses
    -0.09
    éĿ¡
    -0.09
    éĵ²
    -0.09
    å¯Ĥå¯ŀ
    -0.09
    åĩ¶æīĭ
    -0.09
    æķĽ
    -0.09
    POSITIVE LOGITS
    æĢĢåŃķ
    0.22
    åŃķ
    0.19
    å¦Ĭå¨ł
    0.19
     pregnancy
    0.18
     pregnant
    0.18
     Pregn
    0.17
    åŃķæľŁ
    0.17
     беÑĢем
    0.16
    preg
    0.15
    åŃķå¦ĩ
    0.15
    Activations Density 0.211%

    No Known Activations