© 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. 11589
    Prev
    Next
    INDEX
    Explanations

    title: "report", "myst", "things", "everything", "society", "help", "great", "please"

    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
    åIJİæľŁ
    -0.24
    éĽĦ
    -0.20
     Weiner
    -0.19
    å¿«æĬ¥
    -0.19
    麻å°Ĩ
    -0.18
    ä¸įåı¯æĪĸ缺
    -0.18
    快讯
    -0.18
    Ñĥй
    -0.18
    rz
    -0.17
    èĭĩ
    -0.17
    POSITIVE LOGITS
     spo
    0.22
    Pros
    0.21
    çļĦçĪ±æĥħ
    0.21
     gul
    0.21
     Pros
    0.20
    *****↵↵
    0.18
    keywords
    0.18
    é£İä¿Ĺ
    0.18
    spo
    0.18
    ilon
    0.18
    Activations Density 0.004%

    No Known Activations