© 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. 11665
    Prev
    Next
    INDEX
    Explanations

    loss or defeat

    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
    æIJª
    -0.22
    æľīä¸Ģå®ļçļĦ
    -0.21
    åŁ¹åħ»
    -0.20
    åŁ¹èĤ²
    -0.20
    Tester
    -0.19
    满
    -0.18
    åĬŁå¾·
    -0.18
     tem
    -0.18
    illation
    -0.18
    éĹ¨æ§Ľ
    -0.17
    POSITIVE LOGITS
    åIJĥäºı
    0.26
    åĬ£åĬ¿
    0.25
    æįŁå¤±
    0.24
    被åĬ¨
    0.23
    éĢĬ
    0.23
     loss
    0.23
     lost
    0.22
    æį
    0.21
    身åŃIJ
    0.20
    æĹłåı¯
    0.20
    Activations Density 0.079%

    No Known Activations