© 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. 36326
    Prev
    Next
    INDEX
    Explanations

    article citations and sources

    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
    éĩįéĩį
    -0.11
    åĨĮ
    -0.10
    æģĴ
    -0.09
    acht
    -0.09
    èµ°å¾Ĺ
    -0.09
    åĩĿ
    -0.09
    央è¡Į
    -0.09
    æ½Ľ
    -0.09
    缤
    -0.08
    貫
    -0.08
    POSITIVE LOGITS
     articles
    0.12
    è¿Ļç¯ĩæĸĩç«ł
    0.12
     article
    0.12
    ä¸Ģç¯ĩ
    0.12
    /articles
    0.12
    æĸĩç«ł
    0.11
     Articles
    0.11
    åıij表
    0.11
    .Article
    0.10
    articles
    0.10
    Activations Density 0.092%

    No Known Activations