© 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. 16146
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    åĦ¿
    -0.23
     меÑĢоп
    -0.20
    AP
    -0.19
    åħĴ
    -0.19
    çĶ¨æ°´
    -0.19
    èĢĥ
    -0.18
     пÑĢиÑıÑĤн
    -0.18
    tures
    -0.18
    è¿Ļåı¥è¯Ŀ
    -0.18
    æľīå¤ļå°ij
    -0.18
    POSITIVE LOGITS
    ä¼ĬåĪ©
    0.20
    볨
    0.20
    天涯
    0.20
    ogne
    0.19
    éĤº
    0.19
     atenção
    0.18
    éķ£
    0.18
    nh
    0.18
    æĸ¯åŁº
    0.18
    PREFIX
    0.17
    Activations Density 0.000%

    No Known Activations