© 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. 11212
    Prev
    Next
    INDEX
    Explanations

    mathematical or programming expressions

    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
    åı¦ä¸Ģä½į
    -0.22
     duo
    -0.20
     Ñħа
    -0.20
    å¦Ĥæŀľä½łæĥ³
    -0.19
    xon
    -0.18
    -split
    -0.18
    欢è¿İæĤ¨
    -0.18
     Lair
    -0.18
    è¿Ļç§įæĸ¹å¼ı
    -0.18
    æĬľ
    -0.18
    POSITIVE LOGITS
    åIJĪ计
    0.25
    æĭ¬
    0.24
    æĿĤ
    0.19
    åľ°ä¸Ń
    0.19
    éĩįçĤ¹é¢ĨåŁŁ
    0.19
    éĩįçĤ¹åħ³æ³¨
    0.19
    ãģ©ãĤĮ
    0.18
    theses
    0.18
    æĺ¯å¤ļå°ij
    0.18
     metav
    0.18
    Activations Density 0.019%

    No Known Activations