© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2319
    Prev
    Next
    INDEX
    Explanations

    QT prolonged / syndrome

    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
     UPDATED
    -0.24
    elles
    -0.22
    æ±Ĥå©ļ
    -0.22
    æīijåħĭ
    -0.22
     genu
    -0.22
     rog
    -0.22
    梵
    -0.22
    çīĪæĿĥ声æĺİ
    -0.22
    oker
    -0.21
     sorry
    -0.21
    POSITIVE LOGITS
    itud
    0.26
    éĺļ
    0.24
    keh
    0.24
    çŁ
    0.24
    inema
    0.23
    nation
    0.23
    icy
    0.23
     Reyn
    0.22
    nard
    0.22
    itude
    0.22
    Activations Density 0.001%

    No Known Activations