© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15001
    Prev
    Next
    INDEX
    Explanations

    prior art or model systems

    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
    çĸ³
    -0.19
    chemes
    -0.19
    osoph
    -0.19
    ẻ
    -0.19
    heets
    -0.19
    éªIJ
    -0.18
    ãģ¨ãĤĬ
    -0.18
    igraph
    -0.18
    cheme
    -0.18
    anson
    -0.17
    POSITIVE LOGITS
    ä¸ĢåĪ»
    0.26
    æĢ§çļĦ
    0.23
    æŶéĹ´åĨħ
    0.22
    æĦı大
    0.22
    à¸Ħà¸ĵะà¸ģรรม
    0.22
    æĥħåĨµä¸ĭ
    0.21
     обÑĢазом
    0.21
    äºĭçī©
    0.21
    æĦıä¹īä¸ĬçļĦ
    0.21
    à¹Ģà¸Ĺà¸Ħà¹Ĥà¸Ļ
    0.21
    Activations Density 0.850%

    No Known Activations