© 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. 12223
    Prev
    Next
    INDEX
    Explanations

    posting messages

    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
    à¸ģรม
    -0.25
    éĺģ
    -0.22
    ä¸įåIJĪéĢĤ
    -0.19
    å·ŀåĮº
    -0.19
     Invest
    -0.18
    注æĺİæĿ¥æºIJ
    -0.18
    æIJľ
    -0.18
    çŃĽ
    -0.17
    çĽĪ
    -0.17
    format
    -0.17
    POSITIVE LOGITS
     Ludwig
    0.18
    side
    0.18
    çĶŁäº§ç»ıèIJ¥
    0.18
    浯
    0.17
     ÑĤоваÑĢов
    0.17
    æĢĿç´¢
    0.17
    gy
    0.17
    pone
    0.17
     vending
    0.17
    .rm
    0.17
    Activations Density 0.032%

    No Known Activations