© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12552
    Prev
    Next
    INDEX
    Explanations

    possessive noun endings ('s)

    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
    åľ¨ä¼łå¥ĩ
    -0.22
    åľ¨äº¬
    -0.22
    æѤæĸĩ
    -0.20
    ãĦ§
    -0.20
    éĴĮ
    -0.20
    è¿Ļ个游æĪı
    -0.20
    аÑĢÑĮ
    -0.20
    éħįæĸĻ
    -0.20
    çī²
    -0.20
    æŃ¹
    -0.19
    POSITIVE LOGITS
    ãĢĮ
    0.25
    ãĢĬ
    0.23
    åįĥ
    0.21
    大åŀĭ
    0.20
    建ç«ĭ
    0.20
    é«ĺ
    0.19
    ë»ĺ
    0.19
    å½¼
    0.19
    åħ¼
    0.18
    å¹»
    0.18
    Activations Density 0.064%

    No Known Activations