© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14930
    Prev
    Next
    INDEX
    Explanations

    celebrity professions

    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
    è¿Ļç§įäºĭæĥħ
    -0.23
    è¿ĻäºĽäºº
    -0.21
    ÑĢа
    -0.21
    åı«æĪij
    -0.19
    éĤ£äºĽ
    -0.19
    ä»ĸ们çļĦ
    -0.19
    åľ¨çݩ家ä¸Ń
    -0.18
    ç»ıéĶĢ
    -0.18
    æĤ
    -0.18
    æĪijåİ»
    -0.18
    POSITIVE LOGITS
    -turned
    0.26
    ä¿©
    0.22
    åħ¼
    0.20
    åIJĮæĹ¶ä¹Łæĺ¯
    0.20
    åıĬåħ¶
    0.19
    éĺĶ
    0.19
     RESOURCE
    0.19
    ä¸İåħ¶
    0.18
    巨头
    0.18
    çĶµåĬĽ
    0.18
    Activations Density 0.050%

    No Known Activations