© 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. 4689
    Prev
    Next
    INDEX
    Explanations

    economic downturns and recessions

    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
    æĹłçŁ¥
    -0.10
    Compat
    -0.09
    åį«åģ¥
    -0.09
     ÑĦиÑĢ
    -0.08
    åħ¬ç¤º
    -0.08
    å·²ç»ıæľīäºĨ
    -0.08
    éľį
    -0.08
    ikon
    -0.08
    åıĭè°Ĭ
    -0.08
    /apple
    -0.08
    POSITIVE LOGITS
    éĩijèŀįåį±æľº
    0.12
    缩水
    0.12
     recession
    0.12
    åħ¨çIJĥç»ıæµİ
    0.11
    æĬĺæī£
    0.11
    åĽŀæļĸ
    0.10
    æĶ¾ç¼ĵ
    0.10
    éĢĨåĬ¿
    0.10
    æĸ°å¸¸æĢģ
    0.10
    æĹ¶ä»£ä¸ŃåĽ½
    0.09
    Activations Density 0.115%

    No Known Activations