© 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. 11491
    Prev
    Next
    INDEX
    Explanations

    sports playoffs and tournaments

    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
    ä½ĵä¼ļ
    -0.20
    éĵ
    -0.20
    åIJ¬äºĨ
    -0.19
    çī©åĵģ
    -0.19
    é¢Ĩä¼ļ
    -0.19
    .rl
    -0.19
    çĤ¹èµŀ
    -0.19
    åŃĸ
    -0.18
    ä¸Ģå¼Ģå§ĭ
    -0.18
    éĵ«
    -0.18
    POSITIVE LOGITS
    asy
    0.22
    æ¯ıå¹´éĥ½
    0.21
    duck
    0.20
    æľīæĦıä¹ī
    0.20
    _CHARS
    0.19
    mom
    0.19
     parach
    0.18
    moth
    0.18
    kus
    0.17
    htt
    0.17
    Activations Density 0.024%

    No Known Activations