© 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. 10967
    Prev
    Next
    INDEX
    Explanations

    semi- followed by descriptors

    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
     beiden
    -0.19
    fulness
    -0.18
    makers
    -0.17
    ../
    -0.17
    making
    -0.16
    ught
    -0.16
     latter
    -0.16
     Fleming
    -0.16
    rie
    -0.16
    æĹłå½¢
    -0.15
    POSITIVE LOGITS
    à¹Ĩ
    0.20
    个å¤ļæľĪ
    0.19
    ArrayOf
    0.19
    主ä¹īæĢĿæĥ³
    0.17
    antically
    0.17
    ilion
    0.17
    uke
    0.17
    çį¨ç«ĭ
    0.17
    overe
    0.16
    ocal
    0.16
    Activations Density 0.022%

    No Known Activations