© 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. 24317
    Prev
    Next
    INDEX
    Explanations

    Archives: followed by topic

    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
    éĩįéĩį
    -0.10
    åĽ¾æĸĩ
    -0.09
    ä»Ĭ天æĪij们
    -0.09
    ALLE
    -0.09
    onders
    -0.08
     Alleg
    -0.08
    壮è§Ĥ
    -0.08
    è¾īçħĮ
    -0.08
    orian
    -0.08
    çŃĶåį·
    -0.08
    POSITIVE LOGITS
    åŃ£
    0.10
     Polo
    0.09
    utes
    0.09
    è°ĭ
    0.09
    _frontend
    0.09
    讯
    0.09
    éŀħ
    0.08
    istan
    0.08
    ISM
    0.08
    æįİ
    0.08
    Activations Density 0.038%

    No Known Activations