© 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. 7845
    Prev
    Next
    INDEX
    Explanations

    dates and times

    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
    ses
    -0.10
    åѵåĮĸåĻ¨
    -0.09
    è¿Ļåħ¶ä¸Ń
    -0.08
    åijĬè¯īä»ĸ
    -0.08
    aland
    -0.08
     silent
    -0.07
    å¼ĥ
    -0.07
    ä¼ļåIJĮ
    -0.07
    ستاÙĨ
    -0.07
    TOOLS
    -0.07
    POSITIVE LOGITS
    ä¸įå¾Ĺä¸į说
    0.09
    çijľ
    0.09
    çµ®
    0.09
    odore
    0.09
    ãģĵãĤĵãģ«ãģ¡ãģ¯
    0.08
    engl
    0.08
    StringUtils
    0.08
    æľ¬æĬ¥è®¯
    0.08
    éľ²
    0.08
    梵
    0.08
    Activations Density 0.826%

    No Known Activations