© 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. 15932
    Prev
    Next
    INDEX
    Explanations

    company suffixes like Ltd, SAS, s.r.o

    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
    èĮ«èĮ«
    -0.19
    yst
    -0.18
     Manit
    -0.18
    èŀŁ
    -0.17
     Hobby
    -0.17
    LBL
    -0.17
    wise
    -0.17
    ׼×IJ
    -0.17
    éķĩæĶ¿åºľ
    -0.16
    ç§ĥ
    -0.16
    POSITIVE LOGITS
    ä¸ĵéŨ
    0.20
    æĢ§è´¨
    0.19
    ç»ıèIJ¥èĮĥåĽ´
    0.18
    æĹ¶æľŁçļĦ
    0.18
    èIJ¥ä¸ļ
    0.18
    å¢ĥ
    0.18
    åĵĦ
    0.18
    olumn
    0.17
    çļĦåıijå±ķ
    0.17
    äºİ
    0.17
    Activations Density 0.031%

    No Known Activations