© 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. 716
    Prev
    Next
    INDEX
    Explanations

    case-control study

    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
    loff
    -0.26
    azz
    -0.23
    ç¸
    -0.23
    zelf
    -0.23
     rubbed
    -0.22
    elope
    -0.22
    ren
    -0.21
     tighter
    -0.21
     poste
    -0.21
    æĭĽçīĮ
    -0.21
    POSITIVE LOGITS
    iced
    0.27
     Orchard
    0.23
     ark
    0.23
    çļĦå½¢å¼ı
    0.23
    Wal
    0.23
     banking
    0.22
    iska
    0.22
     Banking
    0.21
     cess
    0.21
     Redistribution
    0.21
    Activations Density 0.994%

    No Known Activations