© 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. 13948
    Prev
    Next
    INDEX
    Explanations

    Jewish, Christian, Catholic, or Indian places

    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
     Huffman
    -0.21
     Appalachian
    -0.20
     Appalach
    -0.20
    俳
    -0.19
    éĴĴ
    -0.19
    usa
    -0.19
    çĤĬ
    -0.19
    izes
    -0.19
    Behavior
    -0.18
    -reader
    -0.18
    POSITIVE LOGITS
    emode
    0.22
    èĢģæĿ¿
    0.20
    antha
    0.20
    åķĨ人
    0.19
    éĢĴ交
    0.19
    åľ¨ä¸Ĭæµ·
    0.19
    æĿĤ
    0.18
    æĴ¤ç¦»
    0.18
    大佬
    0.18
    å¸IJåı·
    0.18
    Activations Density 0.101%

    No Known Activations