© 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. 37334
    Prev
    Next
    INDEX
    Explanations

    you + verb

    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
    ever
    -0.10
    æģ¤
    -0.09
    ç«¥
    -0.09
    éĥ¨åī¯
    -0.08
    éļĻ
    -0.08
    ä¸į大
    -0.08
    å¾Īé«ĺåħ´
    -0.08
    樯
    -0.08
    å°±æĺ¯åĽłä¸º
    -0.08
    ç»ıéªĮåĢ¼
    -0.08
    POSITIVE LOGITS
    ä»Ģä¹Īæł·çļĦ
    0.13
    æĢİ
    0.13
    ¿
    0.12
    æľīä½ķ
    0.12
     ¿
    0.12
    äºĨåIJĹ
    0.11
    åĵªäºĽ
    0.11
    ä½ķç§į
    0.11
    ãģ¯ãģ©ãģĨ
    0.10
    æĺ¯ä¸įæĺ¯
    0.10
    Activations Density 0.492%

    No Known Activations