© 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. 59189
    Prev
    Next
    INDEX
    Explanations

    for organizations

    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
    æĶ¶åĪ°äºĨ
    -0.09
    æ»Ĺ
    -0.08
    è¡Įäºĭ
    -0.08
     Bund
    -0.08
    人大
    -0.08
    ä¸įå®ļ
    -0.08
     Loft
    -0.08
    èĬ¸
    -0.08
     Paulo
    -0.08
     barr
    -0.08
    POSITIVE LOGITS
    ä¹ħäºĨ
    0.09
    ATES
    0.09
    uet
    0.09
    _CHK
    0.09
    æ´ģåĩĢ
    0.08
    è¿ĩåħ³
    0.08
    opi
    0.08
    ToF
    0.08
    irl
    0.08
    ges
    0.08
    Activations Density 0.033%

    No Known Activations