© 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. 16799
    Prev
    Next
    INDEX
    Explanations

    academic degrees and diplomas

    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
    ä½ıæĪ¿åħ¬ç§¯
    -0.20
    ç¦ģåĮº
    -0.20
    /fixtures
    -0.19
    ç§ijæĬĢèĤ¡ä»½
    -0.19
    å·¡åĽŀ
    -0.18
     (:
    -0.18
    yas
    -0.18
    为主é¢ĺ
    -0.18
    à¸Ļà¹Ĥย
    -0.17
    éľ¹
    -0.17
    POSITIVE LOGITS
    è¯ģ书
    0.26
    æ¯ķä¸ļ
    0.26
    称åı·
    0.25
    é¢ģåıij
    0.25
    ä¸Ģå¹´å¤ļ
    0.25
    åѦä½į
    0.24
    Completion
    0.24
     finished
    0.24
    finished
    0.24
     completion
    0.23
    Activations Density 0.045%

    No Known Activations