© 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. 11935
    Prev
    Next
    INDEX
    Explanations

    utf-8 encoding

    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
    çĶ¨
    -0.20
    ÑĩÑĢежден
    -0.20
     PaÅĦstwo
    -0.20
     dame
    -0.20
    ä¸ĢæŃ¥
    -0.19
    该
    -0.19
    æ³ķå®ļ
    -0.18
    çĬ¯
    -0.18
    éĩįçĤ¹
    -0.18
     desn
    -0.18
    POSITIVE LOGITS
    æľīçļĦçݩ家
    0.20
    鹫
    0.20
    (links
    0.20
    好çİ©
    0.19
    ypi
    0.19
    çļĦæĸ¹å¼ıæĿ¥
    0.19
    wdx
    0.19
    çĽĺçĤ¹
    0.19
    åľ¨çݩ家ä¸Ń
    0.19
    æł¼å°ĩ
    0.19
    Activations Density 0.005%

    No Known Activations