© 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. 14825
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Siber
    -0.22
    loat
    -0.20
     Orth
    -0.19
    é»ijé¾Ļæ±Łçľģ
    -0.18
    çŁ¿æ³īæ°´
    -0.18
    orth
    -0.18
    agements
    -0.18
    ä¿Ħç½Ĺæĸ¯
    -0.17
    å¾Ĺä½ı
    -0.17
    æ¿ĢçĥĪçļĦ
    -0.17
    POSITIVE LOGITS
    .orange
    0.18
    æĭĽçĶŁ
    0.18
    èī²ç´ł
    0.18
    Coder
    0.18
    erior
    0.18
    壤
    0.17
     powder
    0.17
    ç¼ģ
    0.17
    etty
    0.17
    æĻºæħ§åŁİå¸Ĥ
    0.17
    Activations Density 0.000%

    No Known Activations