© 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. 12126
    Prev
    Next
    INDEX
    Explanations

    living in

    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
     bedtime
    -0.18
    æ´
    -0.18
    è·ĭ
    -0.18
    åĴ½
    -0.18
    ç«ĭ项
    -0.18
     зÑĢениÑı
    -0.17
    å¼ĢåѦ
    -0.17
    forth
    -0.17
    åĩºçĤī
    -0.17
    åħ¥åľº
    -0.17
    POSITIVE LOGITS
    agra
    0.20
    /do
    0.19
    ä¸įå®ī
    0.17
    å¨ĺ家
    0.17
    acks
    0.17
    ied
    0.17
    .opensource
    0.17
    主ä¹īèĢħ
    0.17
     quarters
    0.16
    éĤ£æł·çļĦ
    0.16
    Activations Density 0.059%

    No Known Activations