© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14887
    Prev
    Next
    INDEX
    Explanations

    diet and healthy eating

    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
    æĥŁ
    -0.23
    çĽ¸äº²
    -0.22
     Toilet
    -0.22
    åĬŀ好
    -0.21
    è¢ĸ
    -0.20
    antee
    -0.19
    mö
    -0.19
    çĿ«æ¯Ľ
    -0.18
    è·ª
    -0.18
    æīĩ
    -0.18
    POSITIVE LOGITS
     Subway
    0.22
    è§Ħå¾ĭ
    0.21
    é¥®é£Ł
    0.21
    ãĥIJãĥ©ãĥ³ãĤ¹
    0.20
    ç´Ĭä¹±
    0.19
    æ¯ıæĹ¥
    0.19
    æ¯ı天
    0.19
     daily
    0.19
     diet
    0.19
     regimen
    0.19
    Activations Density 0.023%

    No Known Activations