© 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. 9258
    Prev
    Next
    INDEX
    Explanations

    to name a few

    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
    ä»ĸ认为
    -0.11
    urai
    -0.09
    nds
    -0.09
    åIJĦæĸ¹
    -0.09
    à¹īà¸ĩ
    -0.08
    ç«ĭå¿Ĺ
    -0.08
    åķľ
    -0.08
    SION
    -0.08
    deps
    -0.08
    åĥ®
    -0.08
    POSITIVE LOGITS
    æĽ´ä½ķåĨµ
    0.11
    ä½ķåĨµ
    0.10
    ä¸į说
    0.10
    éļ¾æĢª
    0.09
    çĶļèĩ³
    0.09
    èĢĥèĻij
    0.09
    çĶļèĩ³æĺ¯
    0.09
    åĪ«çļĦ
    0.09
    è¿ĺæľīå¾Īå¤ļ
    0.09
    åĬłä¸Ĭ
    0.09
    Activations Density 0.031%

    No Known Activations