© 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. 12285
    Prev
    Next
    INDEX
    Explanations

    these followed by a noun

    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
    íĹĢ
    -0.24
    è¿Ļç¯ĩ
    -0.21
    æĹłè®º
    -0.20
    严éĩį
    -0.19
    æĬ¥åijĬæĺ¾ç¤º
    -0.19
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.19
    İĺìĿ´ì§Ģ
    -0.19
    çīĪæľ¬
    -0.19
    è¿Ļ两个
    -0.19
    è¿Ļç¯ĩæĸĩç«ł
    -0.19
    POSITIVE LOGITS
    /th
    0.22
    è¾ĺ
    0.20
    лÑıем
    0.20
    ÑĢеÑģ
    0.20
     же
    0.20
    嵩
    0.19
     SAME
    0.19
    èĬĻ
    0.18
    èģ¿
    0.18
    èĢģ乡
    0.18
    Activations Density 0.149%

    No Known Activations