© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 746
    Prev
    Next
    INDEX
    Explanations

    talents, welcomed, lucky

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    è¿ĩåħ³
    -0.27
     Overrides
    -0.23
    izards
    -0.23
    feas
    -0.23
     Override
    -0.23
    éĢĤåIJĪèĩªå·±
    -0.23
    éĴĪ对æĢ§
    -0.22
    å¥Ĺé¤IJ
    -0.22
    æ¯ıåij¨
    -0.22
    å©ļåIJİ
    -0.22
    POSITIVE LOGITS
    人æīį
    0.36
    çľĭä»ĸ
    0.33
    è¿Ļ个人
    0.31
    çij°
    0.31
     talents
    0.29
     welcomed
    0.29
    ä»»åij½
    0.28
    è¿Ļä½į
    0.28
     talent
    0.28
    欢è¿İ
    0.28
    Activations Density 0.109%

    No Known Activations