© 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. 10392
    Prev
    Next
    INDEX
    Explanations

    of regulation, of yesterday, of MLS

    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
    apia
    -0.08
    åĩ¡äºĭ
    -0.08
    NFL
    -0.08
    馥
    -0.08
    ouce
    -0.08
     TSA
    -0.08
    scape
    -0.08
    ê¹ĥ
    -0.08
    _REST
    -0.08
    éĤ£äºº
    -0.08
    POSITIVE LOGITS
    漫éķ¿çļĦ
    0.10
    æ·ŀ
    0.09
    èŁł
    0.09
    æľ¬å¸Ĥ
    0.09
    åĨĽè®Ń
    0.09
    åģĮ
    0.09
    æĸ°ä¸Ģè½®
    0.09
    壬
    0.08
    aux
    0.08
     каждой
    0.08
    Activations Density 0.025%

    No Known Activations