© 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. 15664
    Prev
    Next
    INDEX
    Explanations

    days of the week followed by a comma

    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
    Pa
    -0.19
     Pace
    -0.19
    oul
    -0.19
    inals
    -0.18
    s
    -0.18
     Rousse
    -0.18
    Disclosure
    -0.17
     Pa
    -0.17
    rag
    -0.17
    çĥ¯
    -0.17
    POSITIVE LOGITS
    æĬ¥åijĬæĺ¾ç¤º
    0.21
    对äºİæĪij们
    0.20
    çļĦè¯Ŀé¢ĺ
    0.20
     اÙĦعÙħ
    0.20
    è¿ĩåIJİ
    0.19
    çļĦä¹IJ趣
    0.19
    å¿«æĬ¥
    0.19
    å½ĵçĦ¶æĺ¯
    0.19
    äºĨ好å¤ļ
    0.18
    _AA
    0.18
    Activations Density 0.027%

    No Known Activations