© 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. 1358
    Prev
    Next
    INDEX
    Explanations

    water reservoirs and dams

    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
     walk
    -0.28
    éĻĮ
    -0.27
    æĴ°åĨĻ
    -0.26
     mob
    -0.26
     unic
    -0.25
     ubiqu
    -0.25
    shop
    -0.24
    æī§ä¸ļ
    -0.24
    æĪij羣çļĦ
    -0.24
    èij©
    -0.24
    POSITIVE LOGITS
    æ°´åºĵ
    0.47
     dams
    0.47
     reservoir
    0.41
    æ°´åĪ©
    0.39
     dam
    0.39
    çĶµç«Ļ
    0.36
    åĿĿ
    0.35
    æ°´åĪ©å·¥ç¨ĭ
    0.35
     irrigation
    0.34
    èĵĦ
    0.33
    Activations Density 0.027%

    No Known Activations