© 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. 13817
    Prev
    Next
    INDEX
    Explanations

    most challenging/difficult/exciting/amazing

    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
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.19
    çģĮæºī
    -0.19
    غا
    -0.19
    æµĵæµĵçļĦ
    -0.19
    éļ¾å¿ĺ
    -0.19
     ÑĤаким
    -0.18
    åĽĽå¤§
    -0.18
    åīįæīĢ
    -0.18
     ole
    -0.18
    ongan
    -0.18
    POSITIVE LOGITS
    èİ«è¿ĩäºİ
    0.31
    åľ¨äºİ
    0.28
     aspects
    0.20
    esty
    0.19
    çŁ¥éģĵäºĨ
    0.19
    åĴ«
    0.19
    æľĢ容æĺĵ
    0.19
    ä¹ĭä¸Ģ
    0.19
    ma
    0.18
    çļĦæĺ¯
    0.18
    Activations Density 0.053%

    No Known Activations