© 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. 13423
    Prev
    Next
    INDEX
    Explanations

    new features and changes

    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
    èĩĤ
    -0.22
     desp
    -0.20
    åĽ°å¢ĥ
    -0.20
    usu
    -0.20
    ustin
    -0.19
    è¿Ļç§įæĸ¹å¼ı
    -0.19
    -bel
    -0.19
    è¿Ļç§įæĥħåĨµ
    -0.19
    -h
    -0.18
    éĩįéĩį
    -0.18
    POSITIVE LOGITS
    æĸ°å¢ŀ
    0.34
    åıĺåĮĸ
    0.32
    çļĦåıĺåĮĸ
    0.32
     changes
    0.29
    æĸ°çļĦ
    0.28
    à¹ĥหม
    0.28
    æĶ¹è¿Ľ
    0.28
    æī©åħħ
    0.28
    æĸ°äº§åĵģ
    0.26
    æĸ°ãģĹãģĦ
    0.26
    Activations Density 0.078%

    No Known Activations