© 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. 11947
    Prev
    Next
    INDEX
    Explanations

    editor replies or letters

    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
     proven
    -0.19
    è¿Ļæĸ¹éĿ¢
    -0.19
     ÑģÑĤоÑĢ
    -0.19
    éĥĹ
    -0.18
     kend
    -0.18
    泯
    -0.18
    åŀŃ
    -0.18
    åİŁæľī
    -0.17
    离
    -0.17
    大èħ¿
    -0.17
    POSITIVE LOGITS
    æĸĩä¸Ń
    0.22
    读åIJİ
    0.21
    æłı缮
    0.21
    说ä»Ģä¹Ī
    0.20
    æľĢåIJİä¸Ģ
    0.20
    稿件
    0.19
    对äºİæĪij们
    0.19
    表æī¬
    0.19
    ymm
    0.19
    ibling
    0.19
    Activations Density 0.115%

    No Known Activations