© 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. 14245
    Prev
    Next
    INDEX
    Explanations

    Browns, Sudan, Foundation, Sydney

    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
    èł¹
    -0.19
    大佬
    -0.19
    ť
    -0.19
    被æĬĵ
    -0.19
    èĢģçĪ·åŃIJ
    -0.18
    æѤæĸĩ
    -0.17
    ç©¿è¶Ĭ
    -0.17
    åĭĿ
    -0.17
    æł²
    -0.17
    éħįæĸĻ
    -0.17
    POSITIVE LOGITS
    çĭ¬çī¹çļĦ
    0.21
    é¦ĸ个
    0.21
    ä¸Ģç»ı
    0.21
    太å°ij
    0.21
    çļĦçĭ¬çī¹
    0.21
    æĢª
    0.20
     pers
    0.20
    ç½ķè§ģ
    0.20
    anmar
    0.19
    æĸ°åįİ社
    0.19
    Activations Density 0.205%

    No Known Activations