© 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. 34222
    Prev
    Next
    INDEX
    Explanations

    lead exposure and developmental defects

    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
    èĥĮ
    -0.10
    è·Į
    -0.09
    ä¸įçĶĺ
    -0.09
    æĸ¹åľĨ
    -0.09
     backs
    -0.09
    .getRoot
    -0.09
    æ¶Į
    -0.08
    æĬ±
    -0.08
    åĬŀ好
    -0.08
    èĥĮéĥ¨
    -0.08
    POSITIVE LOGITS
    åİĨ
    0.11
    æľĪä¸Ń
    0.10
    æ¯ķç«Łæĺ¯
    0.10
    ãģ¤ãģĭ
    0.09
    çĶŁæ®ĸ
    0.09
    累积
    0.09
    åİĭè¿«
    0.09
    ä¼IJ
    0.08
    Floor
    0.08
    åIJ¸åıĸ
    0.08
    Activations Density 0.155%

    No Known Activations