© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 51665
    Prev
    Next
    INDEX
    Explanations

    resistance to

    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
    ä½ĵè´¨
    -0.11
    åijĬ
    -0.11
    ç»ıåİĨäºĨ
    -0.11
    olars
    -0.10
    éĺ²æŃ¢
    -0.10
    ç¥Ń
    -0.10
    è¾ĵ
    -0.09
    æ¸ħåĩī
    -0.09
    emean
    -0.09
    èµ·æĿ¥
    -0.09
    POSITIVE LOGITS
    ä»»ä½ķå½¢å¼ı
    0.11
    é«ĺä½İ
    0.10
    é£İ鼨
    0.10
    èĽĬ
    0.09
    滥ç͍
    0.09
    æĸĩåĮĸåĴĮ
    0.09
    öffentlich
    0.09
    ä»»ä½ķ
    0.08
    åIJŃ
    0.08
    é£İåIJ¹
    0.08
    Activations Density 0.054%

    No Known Activations