© 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. 16346
    Prev
    Next
    INDEX
    Explanations

    code initialization

    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
    alus
    -0.20
    Ãłng
    -0.20
    iku
    -0.19
    éļĶå£ģ
    -0.19
    çĸĹæķĪ
    -0.19
    æĦıæĥ³ä¸įåĪ°
    -0.19
    æ¸ļ
    -0.18
    å¿ı
    -0.18
    æ¯ģ
    -0.18
    ark
    -0.17
    POSITIVE LOGITS
     Stall
    0.19
    温度
    0.19
     yazılı
    0.19
     Iss
    0.19
     ëıĮ
    0.19
     blah
    0.19
    æĪĸ
    0.18
    ãģ«ãģ¦
    0.18
    人æĢ§
    0.18
    umbo
    0.18
    Activations Density 0.010%

    No Known Activations