© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 47629
    Prev
    Next
    INDEX
    Explanations

    the best

    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
    Negative Logits
    æīŃæĽ²
    -0.09
    æİ¨è¿Ł
    -0.09
    ught
    -0.08
    ä¸ĸçķĮä¸ĬæľĢ
    -0.08
    å°ıæŶåīį
    -0.08
    éªļ
    -0.08
    åı²ä¸ĬæľĢ
    -0.08
    éĩįä»»
    -0.08
    缸åħ³åĨħ容
    -0.08
    ä¸ĢåĽŀäºĭ
    -0.08
    POSITIVE LOGITS
    spe
    0.10
    ä¹ŁåĽłæѤ
    0.10
    éħį
    0.09
    pard
    0.09
    iode
    0.09
    è¯Ŀ说
    0.08
    è´¨éĩı管çIJĨ
    0.08
    ä¼´æľī
    0.08
     initial
    0.08
    æķ´ä¸ª
    0.08
    Activations Density 0.153%

    No Known Activations