© 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. 16189
    Prev
    Next
    INDEX
    Explanations

    groups of people

    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
    é³ľ
    -0.19
    ä¸ĩæĪ·
    -0.19
    åĩłä½į
    -0.19
    è¶Ĭ大
    -0.19
     billions
    -0.19
    åĬŀ好
    -0.18
    æĭĽèĤ¡
    -0.18
    ',['../
    -0.18
    çļĦæľĭåıĭ
    -0.17
     :+:
    -0.17
    POSITIVE LOGITS
    -plus
    0.26
    å·¦åı³
    0.24
     non
    0.23
    äºĭçī©
    0.21
    ä¸įåIJĮç±»åŀĭ
    0.21
    -member
    0.21
    以ä¸ĬçļĦ
    0.20
    大大å°ıå°ı
    0.20
     extra
    0.20
    åIJĦç±»
    0.20
    Activations Density 0.141%

    No Known Activations