© 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. 13889
    Prev
    Next
    INDEX
    Explanations

    as follows or like this

    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
    oss
    -0.20
    æĦıä¹ī
    -0.20
    à¸Ńำà¸Ļวยà¸Ħวาม
    -0.20
    ä¸į代表
    -0.19
    æ¯ı个
    -0.19
    à¸Ħà¸ĵะà¸ģรรม
    -0.19
    侯
    -0.19
    æīĢæľī
    -0.19
    à¹Ģà¸Ĺà¸Ħà¹Ĥà¸Ļ
    -0.19
     Lou
    -0.19
    POSITIVE LOGITS
    å¦Ĥä¸ĭ
    0.64
    :↵
    0.51
    :↵↵
    0.50
    ï¼ļ↵
    0.48
    ï¼ļ↵↵
    0.48
    以ä¸ĭ
    0.46
     ëĭ¤ìĿĮê³¼
    0.44
    以ä¸ĭåĩłä¸ª
    0.44
    以ä¸ĭãģ®
    0.38
     Ñģлед
    0.36
    Activations Density 0.628%

    No Known Activations