© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 174
    Prev
    Next
    INDEX
    Explanations

    divorce, custody, parenting

    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
    大å¸Ī
    -0.29
    饱åĴĮ
    -0.26
    大æķ°æį®
    -0.26
    åIJŀåĻ¬
    -0.25
     saturated
    -0.25
     satur
    -0.25
     susceptibility
    -0.25
    æİĴè¡Įæ¦ľ
    -0.25
    iron
    -0.24
    çĽĽå®´
    -0.24
    POSITIVE LOGITS
     remar
    0.43
    æĬļåħ»
    0.42
     custody
    0.35
     parenting
    0.35
    åĪĨ离
    0.33
    åŃIJ女
    0.32
    ä¸įåIJĮæĦı
    0.32
     estr
    0.32
     divorced
    0.30
    对åŃ©åŃIJ
    0.30
    Activations Density 0.027%

    No Known Activations