© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51209
    Prev
    Next
    INDEX
    Explanations

    disease outbreaks

    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
    Not in Any Lists

    No Comments

    Negative Logits
    éļıæīĭ
    -0.09
    æł¹åºķ
    -0.09
     dm
    -0.08
    ots
    -0.08
    à¹Į
    -0.08
     Belmont
    -0.08
    æł¹æľ¬ä¸į
    -0.08
    _bel
    -0.08
    主èIJ¥ä¸ļåĬ¡
    -0.08
    æĺ¯æľĢ好çļĦ
    -0.08
    POSITIVE LOGITS
    åľŃ
    0.10
    èıĸ
    0.09
    _ctor
    0.09
     McConnell
    0.09
    _ASCII
    0.09
    ä¸įæĸŃå¢ŀ强
    0.09
    umes
    0.09
    BOSE
    0.08
    éĢ¸
    0.08
    ä¸Ģå°ģ
    0.08
    Activations Density 0.003%

    No Known Activations