© 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. 38595
    Prev
    Next
    INDEX
    Explanations

    risk, disease, society, cancer

    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
    å¿«æĬ¥
    -0.09
    éªģ
    -0.09
    åij¼åĴĮ
    -0.09
    åŀĽ
    -0.09
    æ±ĩéĽĨ
    -0.09
    oky
    -0.09
    ä¼łæĿ¥
    -0.09
    erring
    -0.08
    æĸĩåĮĸåĴĮ
    -0.08
    ä¼ģä¸ļåĴĮ
    -0.08
    POSITIVE LOGITS
    çļĦåħ³ç³»
    0.13
    åģļåĪ°äºĨ
    0.09
    ç²¾
    0.09
    SetName
    0.08
    æĺ¯ä¸įä¼ļ
    0.08
    rush
    0.08
    åijĨ
    0.08
    ä¸Ģèµ·åİ»
    0.08
    éķĬ
    0.08
    窨
    0.08
    Activations Density 0.236%

    No Known Activations