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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21249
    Prev
    Next
    INDEX
    Explanations

    childbirth

    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
    被åĬ¨
    -0.12
    ä¸ļä½Ļ
    -0.10
    ç¼¢
    -0.09
    æѧ
    -0.09
     Passive
    -0.09
    ENO
    -0.09
    è¯İ
    -0.09
    娱
    -0.08
    çļĦçħ§çīĩ
    -0.08
    ä»·ä½į
    -0.08
    POSITIVE LOGITS
    åĪĨ娩
    0.14
    产å¦ĩ
    0.13
     childbirth
    0.12
    产åIJİ
    0.12
     parity
    0.11
    æ¯įå©´
    0.10
     birth
    0.10
    parity
    0.09
    åŃķ
    0.09
     births
    0.09
    Activations Density 0.128%

    No Known Activations