© 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. 33466
    Prev
    Next
    INDEX
    Explanations

    sorting arrays and elements

    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
    个å¤ļ
    -0.10
    ewire
    -0.09
    éģİãģİ
    -0.09
    ãģĻãģİ
    -0.09
    åı¸
    -0.09
    onaut
    -0.09
    åģı离
    -0.09
    å¦ĤæĦı
    -0.09
     Dil
    -0.08
    (solution
    -0.08
    POSITIVE LOGITS
    æİĴåºı
    0.16
     sorting
    0.13
     sort
    0.13
     Sorting
    0.12
    sort
    0.11
     sorter
    0.11
    Sort
    0.11
    _sort
    0.11
     sorted
    0.11
    -sort
    0.11
    Activations Density 0.237%

    No Known Activations