© 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. 2452
    Prev
    Next
    INDEX
    Explanations

    beauty products, colors, lipstick

    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
    汩
    -0.29
    éģĹåĿĢ
    -0.27
    èĵij
    -0.26
    侥幸
    -0.25
     GNUNET
    -0.25
     farms
    -0.25
    gnu
    -0.25
     sông
    -0.25
    åĸĦæĦı
    -0.25
    jc
    -0.24
    POSITIVE LOGITS
     lipstick
    0.40
    èī²å½©
    0.40
    åĮĸå¦Ĩ
    0.39
     color
    0.39
     colour
    0.37
    å¦Ĩ
    0.37
    é¢ľèī²
    0.36
    _colors
    0.35
    èī²
    0.35
     colors
    0.35
    Activations Density 0.031%

    No Known Activations