© 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. 309
    Prev
    Next
    INDEX
    Explanations

    history, science, philosophy, ethics, medicine

    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
    æĴķ
    -0.24
    éľľ
    -0.24
    娱ä¹IJ
    -0.24
     Municip
    -0.24
     lyric
    -0.24
    æ²ĵ
    -0.23
    weekday
    -0.23
    赪
    -0.23
    Republican
    -0.23
     dictatorship
    -0.22
    POSITIVE LOGITS
    ç§ijåŃ¦å®¶
    0.32
    ç§ijåѦ
    0.31
     science
    0.30
     Science
    0.30
    ç§ijæĻ®
    0.30
     scientific
    0.30
    science
    0.29
    ç§ijåįı
    0.29
     scientists
    0.28
     biomedical
    0.28
    Activations Density 0.062%

    No Known Activations