© 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. 14840
    Prev
    Next
    INDEX
    Explanations

    'author:' entries

    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
    嶷
    -0.18
    iele
    -0.17
    vic
    -0.17
    寺
    -0.17
     Reynolds
    -0.17
    æĿ¡
    -0.17
    该项
    -0.17
    graduate
    -0.17
    www
    -0.16
    å¸Ĥæ°ij
    -0.16
    POSITIVE LOGITS
    ä¸ĢçĻ¾
    0.18
    å¦ĤæľŁ
    0.18
    æ®Ĭ
    0.18
    fallback
    0.17
    æĸ¼æĺ¯
    0.17
    ãĬĹ
    0.17
    unning
    0.17
    æ°´æĻ¶
    0.16
    åĢ¬
    0.16
    çļĦçŁ¥è¯Ĩ
    0.16
    Activations Density 0.018%

    No Known Activations