© 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. 12524
    Prev
    Next
    INDEX
    Explanations

    copyright and licensing information

    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
     มà¸ģร
    -0.23
     à¸ŀฤษ
    -0.22
    å¾Ĵ
    -0.21
    ç§ijåĪĽæĿ¿
    -0.20
    å½¹
    -0.20
    ÑĤики
    -0.20
    à¹Ģà¸Ĺศà¸ģา
    -0.19
     ãĥĪãĥ©ãĥĥãĤ¯
    -0.19
    oom
    -0.19
    íĺķ
    -0.19
    POSITIVE LOGITS
    çīĪæĿĥå½Ĵ
    0.21
     echang
    0.21
     Greene
    0.20
    ⣷
    0.19
    ystack
    0.19
     danmark
    0.19
    âĨĽ
    0.19
    romo
    0.19
     taxp
    0.19
     norge
    0.19
    Activations Density 0.049%

    No Known Activations