© 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. 2673
    Prev
    Next
    INDEX
    Explanations

    clothing and outfits

    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
    èĦĨ
    -0.28
    krä
    -0.25
     Granite
    -0.24
    à¹Ĥà¸ķ
    -0.23
    éĹŃ
    -0.23
    æĻ¶ä½ĵ
    -0.22
     guit
    -0.21
    æł¸çĶµ
    -0.21
    çľ¼ä¸ĭ
    -0.21
     minds
    -0.21
    POSITIVE LOGITS
     worn
    0.46
     attire
    0.36
    è¡£
    0.35
    æīĵæī®
    0.34
    æľį饰
    0.34
     wearer
    0.33
     одеж
    0.32
    褴
    0.30
    è¡£æľį
    0.29
     clothes
    0.29
    Activations Density 0.041%

    No Known Activations