© 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. 16122
    Prev
    Next
    INDEX
    Explanations

    celebrity names

    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
    æĺ¯è°ģ
    -0.20
    kea
    -0.19
    æĬ¬å¤´
    -0.19
    okit
    -0.18
    uries
    -0.18
    è¹Ī
    -0.18
    ä¹Łæĺ¯ä¸Ģ个
    -0.18
    说çļĦè¯Ŀ
    -0.17
    对åŃ©åŃIJ
    -0.17
    glass
    -0.17
    POSITIVE LOGITS
    åıĬåħ¶
    0.25
    çļĦåħ´è¶£
    0.22
    并ä¸İ
    0.21
    ¶Ī
    0.20
    æĹħè¡Į
    0.20
    blr
    0.20
    è°¯
    0.19
    æĴ®
    0.19
    æīĢåľ¨çļĦ
    0.19
    åıĬ缸åħ³
    0.19
    Activations Density 0.031%

    No Known Activations