© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3
    Prev
    Next
    INDEX
    Explanations

    clothing related items

    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
    abouts
    -0.20
    à°Ĺ
    -0.20
    iqu
    -0.20
    crud
    -0.19
    wards
    -0.19
     deadly
    -0.18
    夷
    -0.18
    亢
    -0.18
    æĸ§
    -0.18
    ween
    -0.18
    POSITIVE LOGITS
    çĶ¨åĵģ
    0.32
    æīĵæī®
    0.28
    shed
    0.28
    裳
    0.25
    less
    0.25
    åĴĮæĬĢæľ¯
    0.22
    ied
    0.22
    å»ĵ
    0.21
    褴
    0.21
    -related
    0.20
    Activations Density 0.006%

    No Known Activations