© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12615
    Prev
    Next
    INDEX
    Explanations

    with followed by a number or figure

    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
    å¦ĤåIJĮ
    -0.21
    hem
    -0.20
    æĹħç¨ĭ
    -0.19
    就好
    -0.19
     nam
    -0.18
     nämlich
    -0.18
     ÐĴедÑĮ
    -0.18
    çĬ¹å¦Ĥ
    -0.18
     hem
    -0.17
    æĹ¢æĺ¯
    -0.17
    POSITIVE LOGITS
     заÑĤ
    0.19
     минималÑĮ
    0.18
    оÑĨен
    0.18
    æµħ
    0.18
    ATIC
    0.17
    å¢ī
    0.17
    æ¯Ķçī¹
    0.17
     اÙĦجÙĨس
    0.17
    LOAD
    0.17
    nten
    0.17
    Activations Density 0.035%

    No Known Activations