© 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. 14443
    Prev
    Next
    INDEX
    Explanations

    religious figures and institutions

    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
    apan
    -0.20
    å¾ģéĽĨ
    -0.19
    äºŃ
    -0.18
    çĮİ
    -0.18
    红楼梦
    -0.17
    伧
    -0.17
    pery
    -0.17
    æĢĤ
    -0.17
    _handling
    -0.17
    èķĻ
    -0.17
    POSITIVE LOGITS
    å®ĹæķĻ
    0.34
    âĽª
    0.24
    æķĻåłĤ
    0.23
     religious
    0.23
     religions
    0.22
    religious
    0.22
     Church
    0.21
    åŁºçĿ£æķĻ
    0.21
     relig
    0.21
    éĥĦ
    0.21
    Activations Density 0.345%

    No Known Activations