© 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. 776
    Prev
    Next
    INDEX
    Explanations

    Kant concept philosophy seminar

    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
    erot
    -0.09
     Crack
    -0.09
    éĢIJ
    -0.08
     Rib
    -0.08
    _pb
    -0.08
    èĵ¬
    -0.08
    åħ¬åħĥåīį
    -0.08
     monet
    -0.08
    _ENTRY
    -0.08
    ution
    -0.07
    POSITIVE LOGITS
    èĭį
    0.10
    éķľ
    0.10
    ç»ĻäºĨæĪij
    0.10
    æĺ¥å¤ı
    0.10
    åĬ¡
    0.09
    绣ä¸Ģ
    0.09
    æł¼å°Ķ
    0.09
    弥补
    0.09
     Dess
    0.09
    è´»
    0.09
    Activations Density 0.029%

    No Known Activations