© 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. 23337
    Prev
    Next
    INDEX
    Explanations

    umbilical cord related

    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
     ÑģкаÑĩ
    -0.10
    夷
    -0.09
     Berk
    -0.08
    ä¸įä½ı
    -0.08
    满
    -0.08
    ç¬Ķ
    -0.08
    伤亡
    -0.08
     Recomm
    -0.08
    å®ŀåĬĽ
    -0.08
    BV
    -0.08
    POSITIVE LOGITS
    æ¯ķç«Łæĺ¯
    0.10
    æ´
    0.09
    kits
    0.09
    æĪij们ä¸Ģèµ·
    0.09
    èĦIJ
    0.09
    ç¡
    0.09
    æ¯ıä¸Ģ个人
    0.09
    妹åŃIJ
    0.09
    åħ±åIJĮåĬªåĬĽ
    0.09
    ç»
    0.09
    Activations Density 0.067%

    No Known Activations