© 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. 2478
    Prev
    Next
    INDEX
    Explanations

    articles

    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
    为人
    -0.23
     mpl
    -0.23
    ippy
    -0.23
     cầm
    -0.22
    scheme
    -0.22
    èģĶéĤ¦
    -0.22
     GitHub
    -0.21
    Visualization
    -0.21
    è½®å»ĵ
    -0.21
    udi
    -0.21
    POSITIVE LOGITS
     articles
    0.33
    æ¯ıæľĪ
    0.31
    articles
    0.30
    æ¯ıæĹ¥
    0.27
     digest
    0.27
    æĸĩç«ł
    0.27
    digest
    0.27
    æıIJä¾Ľä¼ĺè´¨
    0.26
    /article
    0.25
    -columns
    0.25
    Activations Density 0.073%

    No Known Activations