© 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. 8862
    Prev
    Next
    INDEX
    Explanations

    delivery and shipping addresses

    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
    åijĽ
    -0.09
     Desmond
    -0.09
    è·Ľ
    -0.09
    imore
    -0.08
    ç½ij讯
    -0.08
    åIJĮæĹ¶ä¹Łæĺ¯
    -0.08
    strap
    -0.08
    æѤäºĭ
    -0.08
    æ¶Ĥ
    -0.08
    èĩªæķij
    -0.08
    POSITIVE LOGITS
    æĮĩå®ļ
    0.11
    èIJ½åľ¨
    0.11
     táºŃn
    0.11
    æĹłç¼Ŀ
    0.11
    éĢģåĪ°
    0.10
    ä¸ĬéŨ
    0.09
    毳
    0.09
    éģ©åIJĪ
    0.08
     specified
    0.08
    å¾Īæĸ¹ä¾¿
    0.08
    Activations Density 0.025%

    No Known Activations