© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 10992
    Prev
    Next
    INDEX
    Explanations

    ideas, trends, growth, culture, information

    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
    对åħ¶çľŁå®ŀ
    -0.20
    اÙĦتز
    -0.20
    ÙħØ·ÙĦ
    -0.20
    笼罩
    -0.20
    ãģªãģĬ
    -0.19
    ç»İ
    -0.19
    إص
    -0.19
    æĹ¶è¾°
    -0.18
    ãģĦãģĨ
    -0.18
    åĿĽ
    -0.18
    POSITIVE LOGITS
    ãĢģ
    0.65
    åĴĮ
    0.59
    åĴĮåıijå±ķ
    0.52
    åĴĮæĬĢæľ¯
    0.52
    åĴĮæľįåĬ¡
    0.51
     and
    0.50
     vÃł
    0.47
     и
    0.47
    à¹ģละ
    0.46
    åĴĮæĶ¯æĮģ
    0.43
    Activations Density 1.200%

    No Known Activations