© 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. 14289
    Prev
    Next
    INDEX
    Explanations

    respective authors or owners

    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
    -esque
    -0.21
    ä¸Ģ个å¤ļ
    -0.19
     Bris
    -0.18
    ç»Ļ
    -0.18
    为人
    -0.17
    被æī§è¡Į
    -0.17
    åīª
    -0.16
    Doc
    -0.16
     Ris
    -0.16
    ä¸Ģé¢Ĺ
    -0.16
    POSITIVE LOGITS
    åĨı
    0.20
    åIJį称
    0.18
    æłĩçļĦ
    0.18
    æİĮéŨ
    0.18
    dong
    0.18
    .Pixel
    0.18
    è®®äºĭ
    0.18
    è°Ĩ
    0.18
    æĢł
    0.18
    Ñģл
    0.17
    Activations Density 0.011%

    No Known Activations