© 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. 1947
    Prev
    Next
    INDEX
    Explanations

    so much or so characteristic

    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
     resend
    -0.24
    åĪ©çī©
    -0.23
    å¾Ĺå¾Ī好
    -0.23
    åı¯è§Ĩ
    -0.23
     Slut
    -0.23
    ä»Ģä¹Īåij¢
    -0.22
    еÑĩение
    -0.22
    å¾Ī大çļĦ
    -0.21
    ounces
    -0.21
    eea
    -0.21
    POSITIVE LOGITS
    AndGet
    0.28
     ÙĪاÙĦØ°ÙĬ
    0.26
     millennia
    0.26
     synonymous
    0.25
     earlier
    0.24
     centuries
    0.24
    贯穿
    0.24
    çļĦéĤ£ä¸ª
    0.23
    åįģåħ«å±Ĭ
    0.23
     by
    0.23
    Activations Density 0.141%

    No Known Activations