© 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. 16034
    Prev
    Next
    INDEX
    Explanations

    improved, enhanced, or reduced

    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
    ä¸Ģ举
    -0.22
    æľĢ好æĺ¯
    -0.18
    å·§
    -0.18
    ä¸Ģé¦ĸ
    -0.18
    ä¸Ģåı¥è¯Ŀ
    -0.18
    å¿ĺäºĨ
    -0.17
    å¾Īå¥½åľ°
    -0.17
    ycles
    -0.17
    dre
    -0.17
    说ä»Ģä¹Ī
    -0.17
    POSITIVE LOGITS
    -than
    0.33
     versions
    0.26
     version
    0.25
    çīĪ
    0.24
    çīĪæľ¬
    0.23
     than
    0.22
    _than
    0.21
    åĴĮå®ĮåĸĦ
    0.20
    /high
    0.20
     funding
    0.20
    Activations Density 0.076%

    No Known Activations