© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 889
    Prev
    Next
    INDEX
    Explanations

    supplement, payment, serving, unit, paper, solution

    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
    æĪIJåĬŁçļĦ
    -0.28
    åį·
    -0.26
    å·¥ä½ľèĢħ
    -0.25
    éĢļéģĵ
    -0.24
    Anne
    -0.24
    ä¸Ģè¡Į
    -0.23
    è¡Į
    -0.23
    åįĩ
    -0.23
    ä¼ł
    -0.23
    åħ¸
    -0.22
    POSITIVE LOGITS
    æ³Ķ
    0.25
     Supplement
    0.24
    æĮīè§Ħå®ļ
    0.24
     Exact
    0.23
     supplemented
    0.23
    åĴĮ个人
    0.23
    æ·º
    0.22
    auc
    0.22
     supplemental
    0.22
     itemprop
    0.22
    Activations Density 0.003%

    No Known Activations