© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10079
    Prev
    Next
    INDEX
    Explanations

    trade union

    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
     Campaign
    -0.09
    ruz
    -0.09
    holm
    -0.08
    éĿĽ
    -0.08
    ç²¾åĬĽ
    -0.08
    Campaign
    -0.08
    书åºĹ
    -0.08
    åĵı
    -0.08
    åĶĽ
    -0.08
    éĦ¯
    -0.08
    POSITIVE LOGITS
    裨
    0.09
    æĪIJåĬŁçİĩ
    0.08
    建设çĶ¨åľ°
    0.08
    鬥
    0.08
    èĤĥ
    0.08
    åı¯éĿłçļĦ
    0.08
    帽åŃIJ
    0.08
    DataProvider
    0.08
    æĪIJç«ĭ以æĿ¥
    0.08
     wr
    0.08
    Activations Density 0.029%

    No Known Activations