© 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. 11666
    Prev
    Next
    INDEX
    Explanations

    amounts or quantities

    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
    acles
    -0.20
    G
    -0.19
    åī¥ç¦»
    -0.19
    âĶ´
    -0.19
    æĸ¹éĿ¢çļĦ
    -0.19
    o
    -0.18
    fh
    -0.18
    æIJľ
    -0.18
    åī¥
    -0.18
    èĿ
    -0.17
    POSITIVE LOGITS
    èĦ¸éĥ¨
    0.22
    åľ©
    0.21
    æľīåĬ©
    0.21
    åģľä¸ĭæĿ¥
    0.21
    é¢Ŀ
    0.20
    ä¸į好æĦıæĢĿ
    0.20
    ä¼ļåĩºçİ°
    0.20
    çĥ
    0.19
    OrCreate
    0.19
    æĸ¹åľĨ
    0.19
    Activations Density 0.053%

    No Known Activations