© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2617
    Prev
    Next
    INDEX
    Explanations

    energy generation and infrastructure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    éķľ
    -0.30
    è¿Ļ段
    -0.26
    çļ®èĤ¤çĹħ
    -0.24
     mirrored
    -0.24
    çĥ§çĥ¤
    -0.23
     Neb
    -0.22
     hotter
    -0.22
    éħįæĸ¹
    -0.22
     Phoenix
    -0.22
    æµĵ度
    -0.22
    POSITIVE LOGITS
    obia
    0.24
    åħ´ä¸ļ
    0.24
    æĺ¯æĪijåĽ½
    0.24
    æĬķèµĦåŁºéĩij
    0.24
    æĪIJ为ä¸ŃåĽ½
    0.23
     gear
    0.23
    éºĵ
    0.23
     Cuomo
    0.23
    abit
    0.23
    åĽĽå·Ŀçľģ
    0.23
    Activations Density 0.005%

    No Known Activations