© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 13232
    Prev
    Next
    INDEX
    Explanations

    plagiarism detection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    xo
    -0.20
    swith
    -0.20
    褪
    -0.19
    áln
    -0.19
    zens
    -0.19
    æĶ¶æ¬¾
    -0.19
     supra
    -0.17
    ê¶Į
    -0.17
    ä¸įåģľçļĦ
    -0.17
    ales
    -0.17
    POSITIVE LOGITS
    essor
    0.21
    åī½
    0.21
    оÑī
    0.19
    ardin
    0.19
    åıįæŃ£
    0.19
    çİĩè¾¾åĪ°
    0.18
    ério
    0.18
     plagiarism
    0.18
    /generated
    0.18
    Ñīин
    0.18
    Activations Density 0.003%

    No Known Activations