© 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. 16616
    Prev
    Next
    INDEX
    Explanations

    describing aspects or attributes

    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
     mostly
    -0.20
     Äijủ
    -0.20
    è¦ģä¹Ī
    -0.20
    mostly
    -0.20
    æĽ·
    -0.19
    ä¹Łå°±
    -0.19
    éĤ£ä¸ĢåĪ»
    -0.18
    owitz
    -0.18
    èģ
    -0.18
    exus
    -0.18
    POSITIVE LOGITS
    家ä½ı
    0.19
    常è§ģçļĦ
    0.19
    é¢ĩ
    0.19
    æĮĩæłĩ
    0.19
    èĩªå·±åĸľæ¬¢
    0.18
    åĢ¼å¾Ĺ注æĦı
    0.18
    çļĦå°±æĺ¯
    0.18
    ç»ı常ä¼ļ
    0.18
    atat
    0.18
    æģ¤
    0.18
    Activations Density 0.136%

    No Known Activations