© 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. 10890
    Prev
    Next
    INDEX
    Explanations

    dates and locations

    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¸įä¸Ĭ
    -0.19
    erd
    -0.18
    çĭĤ
    -0.18
    æ¯ıä¸Ģ次
    -0.18
     thereby
    -0.18
    津贴
    -0.17
    湫
    -0.17
    iche
    -0.17
    æ¤ħ
    -0.17
    è´¸
    -0.17
    POSITIVE LOGITS
    due
    0.22
    åİŁåĽłæĺ¯
    0.21
    çĶŁäº§åĴĮ
    0.20
    /Open
    0.20
    Eat
    0.19
    kan
    0.19
    åĽłåħ¶
    0.19
    pmat
    0.19
    Pie
    0.18
    elmet
    0.18
    Activations Density 0.010%

    No Known Activations