© 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. 63968
    Prev
    Next
    INDEX
    Explanations

    visa and residency requirements

    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
    rim
    -0.09
    éľĦ
    -0.09
    æĥ³æĥ³
    -0.09
    ç¥ĸ
    -0.09
    oman
    -0.09
    ä¸įåłª
    -0.09
    ä¸īæľŁ
    -0.08
    éŨæĪ·ç½ijç«Ļ
    -0.08
    ness
    -0.08
    è¡¥é½IJ
    -0.08
    POSITIVE LOGITS
    qus
    0.09
    ìĺ¤ëĬĶ
    0.08
    çīĸ
    0.08
    æĺ¶
    0.08
    pron
    0.08
    ë£Į
    0.08
    faculty
    0.08
    brains
    0.08
    notations
    0.08
     pron
    0.08
    Activations Density 0.002%

    No Known Activations