© 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. 15315
    Prev
    Next
    INDEX
    Explanations

    air quality / pollution

    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
     hus
    -0.19
    .Std
    -0.19
    们çļĦ
    -0.18
    roy
    -0.18
    åįłåľ°éĿ¢ç§¯
    -0.18
    åĺĺ
    -0.18
    æĮ¨
    -0.17
    移åĪ°
    -0.17
    们
    -0.17
    æ¦Ī
    -0.17
    POSITIVE LOGITS
    æĹłå¿§
    0.23
    æĸ¹éĿ¢çļĦ
    0.23
    çĬ¶åĨµ
    0.21
    çİ°çĬ¶
    0.21
    .nasa
    0.20
    èĶ½
    0.19
    æķ´æ²»
    0.19
    /environment
    0.19
    utow
    0.19
     Futures
    0.18
    Activations Density 0.022%

    No Known Activations