© 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. 1841
    Prev
    Next
    INDEX
    Explanations

    items in stock or inventory

    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
     Airways
    -0.27
    çķ´
    -0.24
    åĬĿ
    -0.23
    awi
    -0.23
    CreatedBy
    -0.23
    .Arguments
    -0.23
    lear
    -0.23
    é¥Ń
    -0.23
    .arguments
    -0.23
    Instructions
    -0.22
    POSITIVE LOGITS
    丰å¯ĮçļĦ
    0.30
    大éĩı
    0.30
    åŃĺè´§
    0.29
     stock
    0.28
    丰å¯Į
    0.28
     availability
    0.28
     live
    0.26
    大éĩıçļĦ
    0.26
    è±IJå¯Į
    0.26
     stocks
    0.25
    Activations Density 0.034%

    No Known Activations