© 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. 14996
    Prev
    Next
    INDEX
    Explanations

    both sides in competition

    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
    ä¸İåıijå±ķ
    -0.20
    æĪijåĴĮ
    -0.20
    æ´»è·ĥ
    -0.19
    _TC
    -0.18
    è¿ĻäºĽäºº
    -0.18
    人ãģ¨
    -0.18
    并ä¸İ
    -0.18
     tg
    -0.18
    icism
    -0.18
    ä¸İæѤ
    -0.17
    POSITIVE LOGITS
    äºĴ
    0.30
    åIJĦèĩª
    0.28
    åĿĩæľī
    0.27
    åIJĦèĩªçļĦ
    0.25
    åIJĦæľī
    0.24
    åħ±åIJĮ
    0.24
    éĥ½æľī
    0.23
     mutually
    0.22
    å½¼æѤ
    0.21
    ãģĿãĤĮãģŀãĤĮ
    0.21
    Activations Density 0.046%

    No Known Activations