© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 919
    Prev
    Next
    INDEX
    Explanations

    energy efficiency or consumption

    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
    uries
    -0.26
    æľīéĴ±
    -0.25
    çķĻè¨Ģ
    -0.24
    解éĻ¤
    -0.23
    çĩĶ
    -0.23
    owitz
    -0.23
    æĶ¾å¼ĥäºĨ
    -0.23
     scraped
    -0.23
    ç´łæĿIJ
    -0.23
    æĬ¹
    -0.22
    POSITIVE LOGITS
    æ¶ĪèĢĹ
    0.34
    æķĪçİĩ
    0.34
    èĬĤ约
    0.32
    èĬĤçľģ
    0.32
     efficiency
    0.32
    浪费
    0.30
    æĪIJæľ¬
    0.29
    èĢĹè´¹
    0.28
    èĥ½èĢĹ
    0.28
     costs
    0.28
    Activations Density 0.042%

    No Known Activations