© 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. 16249
    Prev
    Next
    INDEX
    Explanations

    season ending or concluding

    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
    æĸ©
    -0.20
     Levine
    -0.19
    çĬģ
    -0.19
    çľ¼çIJĥ
    -0.19
    ç«ĭ
    -0.18
     leve
    -0.18
     infl
    -0.18
    åħ¶ä¸Ńä¹ĭä¸Ģ
    -0.18
    è®°ä½ı
    -0.18
     boldly
    -0.18
    POSITIVE LOGITS
     last
    0.22
    çĿ£å¯Ł
    0.21
    -last
    0.21
    ccb
    0.20
    æĮģç»Ńæİ¨è¿Ľ
    0.20
    åĢ®
    0.19
     últimos
    0.19
    Last
    0.19
    æľĢåIJİä¸Ģ次
    0.19
    iasco
    0.19
    Activations Density 0.069%

    No Known Activations