© 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. 11887
    Prev
    Next
    INDEX
    Explanations

    incumbent president's term

    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
    æ°´æŀľ
    -0.21
    ä½IJ
    -0.21
    çĤ¹å¤ļ
    -0.20
    ç½ijçĤ¹
    -0.20
    æĶ¶åĪ°äºĨ
    -0.20
    ä¸ī天
    -0.19
    交éĢļå®īåħ¨
    -0.19
    æĹ¥æŃ£å¼ı
    -0.18
    imoto
    -0.18
    æ¿Ĵ
    -0.18
    POSITIVE LOGITS
    å¹´éĻIJ
    0.27
    ipe
    0.24
    ä»»èģĮ
    0.23
     cum
    0.21
    éĻIJåĪ¶
    0.20
    cum
    0.20
    UTION
    0.20
    лим
    0.19
    æī§æĶ¿
    0.19
    ocracy
    0.19
    Activations Density 0.008%

    No Known Activations