© 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. 13669
    Prev
    Next
    INDEX
    Explanations

    about doing something

    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
    寮
    -0.19
     ë§ŀ
    -0.18
    OfWork
    -0.18
    ë§ŀ
    -0.18
    /company
    -0.17
    emic
    -0.17
    åįµ
    -0.17
    è´¯
    -0.16
    tá
    -0.16
     occurring
    -0.16
    POSITIVE LOGITS
    çļĦæĺ¯
    0.23
    çļĦæĹ¥åŃIJéĩĮ
    0.21
    é¦ĸåħĪæĺ¯
    0.19
    ä»ħä»ħæĺ¯
    0.19
    çļĦ人éĥ½
    0.19
    æķ´ä¸ª
    0.18
    ä¸į论æĺ¯
    0.18
    ä¸įä»ħä»ħæĺ¯
    0.17
    ä¹ĭå¤Ħ
    0.17
    æĪ½
    0.17
    Activations Density 0.050%

    No Known Activations