© 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. 11545
    Prev
    Next
    INDEX
    Explanations

    laicité, Boat, Bush, tumor, agas

    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
    æĦŁæ¿Ģ
    -0.19
    umpt
    -0.18
    ÄIJT
    -0.18
    äºĶå®ĺ
    -0.18
    大å¥ĸ
    -0.18
    pta
    -0.18
    çįŃ
    -0.18
    -blind
    -0.18
     GRAT
    -0.17
    ç¿Ĭ
    -0.17
    POSITIVE LOGITS
    ä¸ŃåĽ½çļĦ
    0.25
    æĺ¯ä¸ŃåĽ½
    0.24
    åľ¨ä¸ŃåĽ½
    0.24
    ä¸ŃåĽ½æĸĩåĮĸ
    0.23
    åĽ½æĥħ
    0.20
    åįİ人
    0.20
    éªĪ
    0.20
    贯穿
    0.19
     Manus
    0.19
    æĸĹ
    0.18
    Activations Density 0.730%

    No Known Activations