© 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
    2. Qwen3-8B
    3. 18-RESID-BATCHTOPK-65K__L0-80
    4. 1304
    Prev
    Next
    INDEX
    Explanations

    stitching and embroidery

    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
    åĴĨ
    -0.30
    çĮ¿
    -0.27
    çĦ¦
    -0.25
     frac
    -0.25
    ä¹Ŀ大
    -0.25
    èѬ
    -0.24
     заÑĢегиÑģÑĤ
    -0.24
    çĮ´
    -0.23
     ÐŁÐ¾Ñĩем
    -0.23
    æĹłæĥħ
    -0.23
    POSITIVE LOGITS
     stitch
    0.47
     embroidery
    0.45
     stitches
    0.41
     stitching
    0.40
     needle
    0.38
    éĴĪ
    0.36
     threads
    0.35
    绣
    0.34
    needle
    0.34
     embroidered
    0.34
    Activations Density 0.010%

    No Known Activations