© 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. 11744
    Prev
    Next
    INDEX
    Explanations

    names ending in -ridge, -ula, -ene, -ar, or surnames

    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
     PaÅĦstwo
    -0.26
     ÐŁÐ¾Ñĩем
    -0.23
     ÐIJлекÑģан
    -0.23
    ê±°ëĤĺ
    -0.21
     Detaylı
    -0.21
    ues
    -0.20
    æĤŃ
    -0.20
    æijĽ
    -0.19
     BaÅŁbakan
    -0.19
     ÐĶмиÑĤÑĢ
    -0.19
    POSITIVE LOGITS
     formerly
    0.23
    æĺ¯ä¸ĢåIJį
    0.23
    ',['../
    0.22
    çļĦ妻åŃIJ
    0.20
    æīĢåľ¨çļĦ
    0.19
    ãģ¨ãģĦãģĪãģ°
    0.19
     (@
    0.19
     milfs
    0.18
    家ä½ı
    0.18
    ä¸ĢåIJį
    0.18
    Activations Density 0.133%

    No Known Activations