© 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. 11650
    Prev
    Next
    INDEX
    Explanations

    rich in nutrients and antioxidants

    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
    âĸ¿
    -0.19
    çĩĥçħ¤
    -0.18
    è£ģ
    -0.18
    è¿Ļç§įæĥħåĨµ
    -0.18
     tent
    -0.18
    ewe
    -0.18
    подоб
    -0.17
     onwards
    -0.17
    orio
    -0.17
    itled
    -0.17
    POSITIVE LOGITS
    丰å¯ĮçļĦ
    0.27
    è±IJå¯Į
    0.24
    åIJ«æľī
    0.23
    丰å¯Į
    0.22
    æĪIJåĪĨ
    0.21
     даннÑĭ
    0.20
    äºĨ大éĩıçļĦ
    0.20
     ÑģодеÑĢжиÑĤ
    0.20
     ÑįнеÑĢги
    0.20
    Both
    0.20
    Activations Density 0.027%

    No Known Activations