© 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. 14965
    Prev
    Next
    INDEX
    Explanations

    business

    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
    ä¹ĭ乡
    -0.23
    èĢģçĪ·
    -0.21
    çĶŁçIJĨ
    -0.20
    ä¸Ģ个éĹ®é¢ĺ
    -0.19
    æľ¬ç§ijçĶŁ
    -0.19
    å¾Ĺä½ı
    -0.19
    arrow
    -0.18
    èĦļä¸ĭ
    -0.18
    åı²è¯Ĺ
    -0.18
    è¦ĨçĽĸçİĩ
    -0.18
    POSITIVE LOGITS
    /business
    0.30
    åĴĮ个人
    0.23
    人士
    0.23
    åģļçĶŁæĦı
    0.23
    尾巴
    0.22
    -government
    0.22
    塾
    0.22
    åĴĮ社ä¼ļ
    0.20
    athe
    0.20
    _sink
    0.20
    Activations Density 0.075%

    No Known Activations