© 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. 15138
    Prev
    Next
    INDEX
    Explanations

    reporting cases and effects

    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
    ä¼ĺè´¨
    -0.21
    PROTO
    -0.21
    tax
    -0.19
    ä¼ĺè´¨çļĦ
    -0.19
    preferences
    -0.19
    cpy
    -0.19
    ä¼Ļ
    -0.19
    .createQuery
    -0.18
    cuts
    -0.18
    ãģIJ
    -0.18
    POSITIVE LOGITS
    æĬ¥åijĬ
    0.31
    ä¸ĬæĬ¥
    0.28
    å¯ĦãģĽ
    0.28
    æĶ¶éĽĨ
    0.27
    åıįé¦Ī
    0.25
    æĬķè¯ī
    0.25
    åł±åijĬ
    0.24
     report
    0.24
    æĪķ
    0.23
    ç´¯
    0.23
    Activations Density 0.047%

    No Known Activations