© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 16995
    Prev
    Next
    INDEX
    Explanations

    jewels, diamonds, emeralds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    éĿ¢åĮħ
    -0.23
    éĨĭ
    -0.22
    æĥĨ
    -0.20
    izza
    -0.20
    ngen
    -0.19
    å®ļåIJij
    -0.19
    éļº
    -0.18
    à¹Ģส
    -0.18
     Bread
    -0.18
    çĻ¾å§ĵ
    -0.18
    POSITIVE LOGITS
    çıłå®Ŀ
    0.30
    å®ĿçŁ³
    0.28
    çijĻ
    0.26
    ðŁĴİ
    0.26
    çĴĢçĴ¨
    0.26
    é¦ĸ饰
    0.26
    累累
    0.25
     diamonds
    0.25
    éĴ»çŁ³
    0.25
    æĪĴæĮĩ
    0.24
    Activations Density 0.027%

    No Known Activations