© 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. 1601
    Prev
    Next
    INDEX
    Explanations

    food items

    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
    æĪIJæŀľ
    -0.25
    ç¢į
    -0.23
     elaborate
    -0.23
    sar
    -0.22
    ibilit
    -0.22
    æ»Ĺ
    -0.22
    建设åĴĮ
    -0.22
     strftime
    -0.21
    ĥģ
    -0.21
    ationally
    -0.21
    POSITIVE LOGITS
     ÐłÐ°Ð·Ð¼ÐµÑĢ
    0.25
    (nx
    0.24
     Bro
    0.23
    (Size
    0.23
    //*
    0.22
    weigh
    0.22
     Downs
    0.22
     weighing
    0.22
    communic
    0.22
    orch
    0.21
    Activations Density 0.094%

    No Known Activations