© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 1093
    Prev
    Next
    INDEX
    Explanations

    articles followed by professions/nationalities

    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
    缴èĩ³
    -0.09
    缴åĪ°
    -0.09
    说ä¸įå®ļ
    -0.08
    åĢļ
    -0.08
    ourg
    -0.08
    ishop
    -0.08
     dec
    -0.08
     even
    -0.08
    omen
    -0.08
    对åѦçĶŁ
    -0.08
    POSITIVE LOGITS
    éĿŀ常好çļĦ
    0.10
    å¹²åĺĽ
    0.10
    éĿŀ常好
    0.10
    å¾Ī好çļĦ
    0.09
    ä¹Ī
    0.09
     currently
    0.09
    å·²ç»ı被
    0.09
    两åıª
    0.09
    çİ°ä»»
    0.09
    è·ŁæĪij说
    0.09
    Activations Density 0.214%

    No Known Activations