© 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. 13362
    Prev
    Next
    INDEX
    Explanations

    is followed by stating words

    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
    ä¸ĵéŨ
    -0.22
    ä¼łåĩº
    -0.21
    称为
    -0.21
    æĬĢæľ¯æĶ¯æĮģ
    -0.20
    侧éĿ¢
    -0.20
    侧
    -0.20
    æľįåĬ¡æ°´å¹³
    -0.20
    空æ°Ķè´¨éĩı
    -0.20
    详ç»Ĩä»ĭç»į
    -0.19
    çĶļèĩ³æĺ¯
    -0.18
    POSITIVE LOGITS
     вÑģегда
    0.20
    æİ®
    0.20
     itself
    0.19
    人人
    0.19
    çĶļä¹Ī
    0.19
    ä¸įåĪĨ
    0.19
     everywhere
    0.18
    ception
    0.18
    ä¸įè¦ģåĨį
    0.18
    ayer
    0.18
    Activations Density 0.102%

    No Known Activations