© 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. 12456
    Prev
    Next
    INDEX
    Explanations

    production or presence

    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
    æľĢæľī
    -0.22
    åĪĨæĺİ
    -0.22
    éĤ£ä¹Ī容æĺĵ
    -0.22
    è¿ĩçļĦ
    -0.21
    æĭ¿æĿ¥
    -0.20
    éķ¿éķ¿
    -0.20
    åīįãģ®
    -0.20
    iếc
    -0.20
    并ä¸įå¤ļ
    -0.19
    è¿ĩå¾Ĺ
    -0.19
    POSITIVE LOGITS
     use
    0.35
    使çĶ¨
    0.28
     налиÑĩие
    0.27
     иÑģполÑĮзованиÑı
    0.26
     relinqu
    0.24
     иÑģполÑĮзование
    0.24
     provision
    0.23
     ability
    0.23
    å¢ŀåĬł
    0.23
    å¼Ģ设
    0.22
    Activations Density 0.469%

    No Known Activations