© 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. 51514
    Prev
    Next
    INDEX
    Explanations

    derivative of

    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
    eries
    -0.10
    exas
    -0.09
    æľīæĿ¡ä»¶çļĦ
    -0.08
     кол
    -0.08
    ç»Ļ大家
    -0.08
    æĹłå¥Ī
    -0.08
    åı¯ä»¥è¯´
    -0.08
     æĽ
    -0.08
    ç»Ļä½łä»¬
    -0.08
    era
    -0.08
    POSITIVE LOGITS
    åģļ好
    0.10
    Ord
    0.10
    çļĦå¿ĥæĢģ
    0.10
    éĺ²åį«
    0.10
    åıªæĥ³
    0.10
    ä¸ĵå¿ĥ
    0.09
    çľ¼åīį
    0.09
    åħ¨åĬĽä»¥èµ´
    0.09
    è¸ıå®ŀ
    0.09
     ordin
    0.09
    Activations Density 0.019%

    No Known Activations