© 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. 14636
    Prev
    Next
    INDEX
    Explanations

    new era or age

    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¨çĶŁæ´»ä¸Ń
    -0.21
    elib
    -0.20
     sẵ
    -0.19
    çľ¼ç¥ŀ
    -0.19
    åºĵ
    -0.19
    走访
    -0.19
    çĪ±åĽ½
    -0.19
    åľ¨äº¬
    -0.19
    _compile
    -0.18
    hợ
    -0.18
    POSITIVE LOGITS
     era
    0.39
    æĹ¶ä»£çļĦ
    0.37
    æĹ¶ä»£
    0.37
    æĹ¶æľŁ
    0.34
    æĻĤ代
    0.33
     Era
    0.33
    -era
    0.32
    çļĦæĹ¶ä»£
    0.31
    åºıå¹ķ
    0.28
    è¿Ļ个æĹ¶ä»£
    0.28
    Activations Density 0.066%

    No Known Activations