© 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. 1081
    Prev
    Next
    INDEX
    Explanations

    reserved under license

    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
    ä¸Ĭå¸Ĥ
    -0.24
    >null
    -0.24
    éªĮè¯ģ
    -0.24
    æŃ¤ä¸¾
    -0.23
     Unified
    -0.23
    mg
    -0.23
    éĩijçīĮ
    -0.23
    æĶ¶å®ĺ
    -0.23
     ENUM
    -0.23
    mes
    -0.23
    POSITIVE LOGITS
     blog
    0.41
     blogging
    0.39
    åįļ客
    0.38
     Blog
    0.35
    /blog
    0.35
     Wordpress
    0.33
    (blog
    0.32
     weblog
    0.32
     blogs
    0.31
    .blog
    0.31
    Activations Density 0.132%

    No Known Activations