© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 55352
    Prev
    Next
    INDEX
    Explanations

    on followed by something

    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
    é©®
    -0.09
    éĺĥ
    -0.09
     Vander
    -0.09
    æݬ
    -0.09
    æĭħå½ĵ
    -0.09
    åı¤ä»Ĭ
    -0.08
    åºŁ
    -0.08
    ëĿ¼ìĿ´
    -0.08
    prov
    -0.08
    è¿Ļè¾¹
    -0.08
    POSITIVE LOGITS
    isser
    0.10
     билеÑĤ
    0.10
    -budget
    0.09
    .toArray
    0.08
    ç¥Ŀ
    0.08
    æĬµæĬĹåĬĽ
    0.08
    èIJ¥
    0.08
    ÑĢож
    0.08
    è¯ģæį®
    0.08
    忧
    0.08
    Activations Density 0.130%

    No Known Activations