© 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. 15923
    Prev
    Next
    INDEX
    Explanations

    bookstore and booksellers

    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
    顺åĪ©å®ĮæĪIJ
    -0.24
    åħ¥å¢ĥ
    -0.23
    çĶ¨æ°´
    -0.22
    åľ¨æ¸¸æĪıä¸Ń
    -0.22
    åľ¨ç¶²è·¯ä¸Ĭ
    -0.21
    imir
    -0.21
     Evel
    -0.20
    ä¿¡æģ¯åħ¬å¼Ģ
    -0.20
    çī©ä½ĵ
    -0.20
    æĦı大
    -0.20
    POSITIVE LOGITS
     bookstore
    0.25
    书åºĹ
    0.24
    书
    0.22
    èĮ¨
    0.21
    genres
    0.21
     Kern
    0.21
     reading
    0.20
    éĤł
    0.20
     cafe
    0.20
    pus
    0.19
    Activations Density 0.017%

    No Known Activations