© 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. 13762
    Prev
    Next
    INDEX
    Explanations

    introducing simplifications

    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
    çī¹æĦı
    -0.21
    ordo
    -0.20
    çī¹ãģ«
    -0.19
    _DISPATCH
    -0.19
    æѤäºĭ
    -0.19
    注æĦı
    -0.19
    ä»ķ
    -0.19
    ди
    -0.19
    磫
    -0.18
     оÑģобенно
    -0.18
    POSITIVE LOGITS
    ä¸Ģåı¥è¯Ŀ
    0.28
    å°±æĺ¯ä¸Ģ个
    0.25
     simply
    0.24
    å°±æĺ¯
    0.24
    :
    0.23
    å°±æĺ¯åľ¨
    0.21
    ãģ¤ãģ¾ãĤĬ
    0.20
     Basically
    0.20
    ãģ«ãģĬ
    0.20
    å°±æĺ¯ä¸ºäºĨ
    0.20
    Activations Density 0.039%

    No Known Activations