© 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. 1880
    Prev
    Next
    INDEX
    Explanations

    numbers and quantities

    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
    è²Į
    -0.25
    ä½ľèĢħæľ¬äºº
    -0.24
    ikt
    -0.22
    è¿Ļä¸ī个
    -0.22
    tern
    -0.21
    åIJIJ
    -0.21
     mx
    -0.21
    ç«ĭæĸ¹
    -0.21
    ä¸īæĸ¹
    -0.21
    åĮķ
    -0.21
    POSITIVE LOGITS
    SelectedItem
    0.26
    åħ¶å®ĥéĹ®é¢ĺ
    0.25
    åIJĦ项
    0.25
    <Item
    0.25
    å¾·æĭī
    0.24
    èĭij
    0.23
    ViewItem
    0.23
     generally
    0.23
    Item
    0.23
     Item
    0.23
    Activations Density 0.646%

    No Known Activations