© 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. 21244
    Prev
    Next
    INDEX
    Explanations

    child's name or relation followed by action/description

    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
    ä¼ī
    -0.10
     Wife
    -0.10
    æŃ¤äºº
    -0.10
     Husband
    -0.09
    è¿Ļ个人
    -0.09
    éģ¿åŃķ
    -0.09
    çĪ±æĥħ
    -0.09
    é«ĺçŃī
    -0.09
    产åIJİ
    -0.09
    女人
    -0.09
    POSITIVE LOGITS
    çİ©èĢį
    0.21
    åĦ¿ç«¥
    0.20
    æĶ¾åѦ
    0.20
    ç«¥
    0.19
    çļĦåŃ©åŃIJ
    0.17
    å°ıåŃ©
    0.16
    åŃ©ç«¥
    0.16
    å°ıåѦçĶŁ
    0.16
    å¤©çľŁ
    0.16
    å°ıçĶ·åŃ©
    0.16
    Activations Density 0.206%

    No Known Activations