© 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. 2919
    Prev
    Next
    INDEX
    Explanations

    drainage and water

    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
     prec
    -0.26
    åħ¨çIJĥ
    -0.26
    æĮij
    -0.23
    èľĺèĽĽ
    -0.23
    å®ļåIJij
    -0.23
     beh
    -0.22
    éĽĨæĪIJ
    -0.22
    ä¸Ģä½ĵåĮĸ
    -0.22
    /language
    -0.22
    æݨçIJĨ
    -0.22
    POSITIVE LOGITS
     brisk
    0.28
    orative
    0.25
    _neighbors
    0.25
     Lutheran
    0.24
    orrow
    0.24
     wastewater
    0.23
     drainage
    0.23
    æ°´éĩı
    0.23
     groundwater
    0.23
    bounce
    0.22
    Activations Density 0.001%

    No Known Activations