© 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. 30097
    Prev
    Next
    INDEX
    Explanations

    copying and plagiarism

    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
    åĨ·éĿĻ
    -0.10
    é³ı
    -0.10
     Fut
    -0.10
    æģ¢
    -0.09
    æĺĶ
    -0.09
    edReader
    -0.09
     trừ
    -0.09
    تÙĬÙĨ
    -0.09
     Programmer
    -0.09
     playable
    -0.09
    POSITIVE LOGITS
    æĬĦè¢Ń
    0.23
    åī½
    0.22
    çĽĹ
    0.16
    çªĥ
    0.14
     copying
    0.14
    åģ·
    0.14
     copied
    0.13
     plagiarism
    0.13
    åĢŁéī´
    0.13
    被çĽĹ
    0.13
    Activations Density 0.123%

    No Known Activations