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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37130
    Prev
    Next
    INDEX
    Explanations

    constitute prior art or precedent

    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
    borg
    -0.10
    姿
    -0.10
    bew
    -0.08
     spl
    -0.08
    æĸ¹å¼ıè¿Ľè¡Į
    -0.08
    éĩĬ
    -0.08
    æĭ¿æĿ¥
    -0.08
    çľ¼è§Ĵ
    -0.07
    æľ¬ç½ijç«Ļ
    -0.07
     Prest
    -0.07
    POSITIVE LOGITS
    åĿļ硬
    0.10
    æ½®
    0.10
    ä¸į该
    0.10
    ä¹Łä¸įæĺ¯
    0.09
    esy
    0.09
    åIJĪæĪIJ
    0.09
    ĭè¯ķ
    0.09
    èĩ¼
    0.09
    èµı
    0.09
     <![
    0.09
    Activations Density 0.008%

    No Known Activations