© 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. 15522
    Prev
    Next
    INDEX
    Explanations

    geopolitical entities and future direction

    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
    é£Łåĵģ
    -0.24
    åĴĮæĶ¯æĮģ
    -0.24
    游æĪıå½ĵä¸Ń
    -0.22
    å°±è¿ij
    -0.21
    家ä¸Ń
    -0.21
    åĽ°æī°
    -0.21
    å¾ĹçŁ¥
    -0.20
    hiếu
    -0.20
    é©»
    -0.20
    åijĬçŁ¥
    -0.20
    POSITIVE LOGITS
    æķ´ä½ĵ
    0.34
     overall
    0.29
    çļĦæķ´ä½ĵ
    0.28
    éĿ¢è²Į
    0.27
    æľªæĿ¥çļĦ
    0.24
    Overall
    0.24
    åħ¨ä½ĵ
    0.24
    åıĺå¾Ĺ
    0.23
    æľªæĿ¥
    0.23
     future
    0.23
    Activations Density 0.067%

    No Known Activations