© 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. 1170
    Prev
    Next
    INDEX
    Explanations

    reproductive outcomes and 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
    åĹ¡
    -0.09
    é¢ģ
    -0.09
    çļĦåģļæ³ķ
    -0.08
    енно
    -0.08
     Gardens
    -0.08
    sphere
    -0.08
     Stroke
    -0.08
    iated
    -0.08
    é²ľæ´»
    -0.08
    build
    -0.08
    POSITIVE LOGITS
    æ¯į
    0.10
    åĵºä¹³
    0.10
    ä½ķåĨµ
    0.09
    ipp
    0.09
    è¿Łè¿Ł
    0.09
    èµŀæĪIJ
    0.09
    èĥľä»»
    0.08
    IP
    0.08
    å¤ĸåĮħ
    0.08
    建ç«ĭåģ¥åħ¨
    0.08
    Activations Density 0.099%

    No Known Activations