© 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. 14494
    Prev
    Next
    INDEX
    Explanations

    lists separated by commas

    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
     bang
    -0.21
    æ°¸è¿ľä¸įä¼ļ
    -0.21
     ÐIJлекÑģан
    -0.20
    HIR
    -0.19
    è¿ĺ
    -0.19
    èİ·
    -0.19
    oop
    -0.18
    iban
    -0.18
    æ°¸ä¸į
    -0.18
     ÐŁÐ¾Ñĩем
    -0.18
    POSITIVE LOGITS
    ÂŃi
    0.24
    åı¯è¾¾
    0.23
     ÙĪغÙĬرÙĩا
    0.20
    rox
    0.20
     similarly
    0.20
    æ·¡åĮĸ
    0.19
    èĶļ
    0.19
     likewise
    0.18
    é»ĦçŁ³
    0.18
     ÑģÑĤоÑĢонÑĭ
    0.18
    Activations Density 0.171%

    No Known Activations