© 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. 13351
    Prev
    Next
    INDEX
    Explanations

    events and social gatherings

    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
    帼
    -0.20
    ream
    -0.20
    æŧ
    -0.20
    é©¾æł¡
    -0.20
    æļijåģĩ
    -0.20
    Extractor
    -0.19
    æĹ¥åŃIJ
    -0.19
    пÑĢакÑĤик
    -0.19
    æīĵæŀ¶
    -0.19
    æĢ»ä½ĵè§ĦåĪĴ
    -0.19
    POSITIVE LOGITS
    礼
    0.21
    社交
    0.21
    éħįä¸Ĭ
    0.20
    å¸Ĥä¸Ńå¿ĥ
    0.20
    åŃĶéĽĢ
    0.20
    ç²¾èĩ´
    0.20
    ä¹ĭå¤ľ
    0.20
    åĹħ
    0.20
     enjoy
    0.20
    Buzz
    0.19
    Activations Density 0.019%

    No Known Activations