© 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. 13172
    Prev
    Next
    INDEX
    Explanations

    part of

    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
     ÐĶмиÑĤÑĢ
    -0.23
    iÃŁ
    -0.21
     заÑĢегиÑģÑĤ
    -0.20
     ÐIJлекÑģан
    -0.20
    ÑĩÑĢежден
    -0.20
    éĿ
    -0.20
    -0.20
     ÐĶм
    -0.19
    tram
    -0.19
    ahoo
    -0.19
    POSITIVE LOGITS
    nehmer
    0.21
    深深çļĦ
    0.20
    æĪij们çļĦ
    0.20
    ../../../
    0.19
    没æľīåĬŀæ³ķ
    0.18
    æĹħç¨ĭ
    0.18
     considerations
    0.18
    漫éķ¿çļĦ
    0.18
    æľ¬ç½ijç«Ļ
    0.17
    åĺ´éĩĮ
    0.17
    Activations Density 0.068%

    No Known Activations