© 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. 11361
    Prev
    Next
    INDEX
    Explanations

    ebooks and books

    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
    fell
    -0.23
    è¾į
    -0.22
    註
    -0.22
    è´´
    -0.19
    éĢł
    -0.19
     Pars
    -0.18
    é¹°
    -0.18
    æĪ¾
    -0.18
    æ±°
    -0.18
    ç¼Ħ
    -0.18
    POSITIVE LOGITS
    ä¸ĭè½½
    0.24
    åĶ®ä»·
    0.23
     Ebook
    0.23
     ebook
    0.23
    download
    0.23
    ä»·ä½į
    0.22
     DOWNLOAD
    0.22
     íĮIJ
    0.21
    -download
    0.21
    iode
    0.21
    Activations Density 0.071%

    No Known Activations