© 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. 2238
    Prev
    Next
    INDEX
    Explanations

    enzyme synthesis

    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
    å¹²æ¶ī
    -0.29
     barber
    -0.27
     wearer
    -0.26
     watches
    -0.25
     Watches
    -0.24
     banners
    -0.23
    éĤ¦
    -0.22
     banner
    -0.22
     wiping
    -0.22
     weather
    -0.21
    POSITIVE LOGITS
    代谢
    0.35
     metabolism
    0.33
    transfer
    0.32
     metabolic
    0.32
    ä¸ĢæŃ¥
    0.31
     metabol
    0.30
    stage
    0.29
    éħIJ
    0.29
    æĶ¶æĶ¯
    0.29
     enzym
    0.28
    Activations Density 0.325%

    No Known Activations