© 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. 16903
    Prev
    Next
    INDEX
    Explanations

    time stamps

    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
    esModule
    -0.21
    å°ıå·§
    -0.19
    åĵŃäºĨ
    -0.19
     вой
    -0.19
    etty
    -0.19
    anus
    -0.19
    åºĶçĶ¨æŁ¥çľĭ
    -0.18
    ÑģÑĤолÑĮ
    -0.18
    Ñģка
    -0.18
    è§ĦèĮĥ
    -0.17
    POSITIVE LOGITS
    æŶåħī
    0.20
    鱿
    0.18
    ä¸Ģçŀ¬éĹ´
    0.18
     block
    0.18
    ablo
    0.18
    æĹ¶æľŁ
    0.18
    la
    0.18
    lem
    0.18
    éĦ
    0.17
    æĸĩç«łæĿ¥æºIJ
    0.17
    Activations Density 0.001%

    No Known Activations