© 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. 15514
    Prev
    Next
    INDEX
    Explanations

    is/are followed by past participle

    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
    æīĢæľī
    -0.24
    æīĢæľīçļĦ
    -0.22
    ä¸ĢèĪ¬çļĦ
    -0.21
    许å¤ļ
    -0.21
    ä¸Ģä¸ĭåŃIJå°±
    -0.21
    ä¸ĢåĪĩéĥ½
    -0.21
    å®Įåħ¨æ²¡æľī
    -0.20
    å¾Ĺå¤ļ
    -0.20
    ä¸Ģ缴åĪ°
    -0.20
    æĽ´å¤ļ
    -0.20
    POSITIVE LOGITS
    ä¸įåIJĮç¨ĭ度
    0.29
    æĪĸå¤ļæĪĸå°ij
    0.23
    åĿĩæľī
    0.23
    æĤī
    0.22
    udes
    0.21
    iance
    0.21
    åĿĩçĶ±
    0.20
    ä¸¥æł¼
    0.20
    æĪĸå¤ļæĪĸ
    0.20
    æĥħåĨµè¿Ľè¡Į
    0.19
    Activations Density 0.075%

    No Known Activations