© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 8985
    Prev
    Next
    INDEX
    Explanations

    clothes and wardrobe

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    åħľ
    -0.10
    ç¬Ķ
    -0.09
    人工
    -0.09
    ä¸ĢåĪ»
    -0.09
    gan
    -0.09
    alis
    -0.09
    .Names
    -0.08
     Interr
    -0.08
    人家
    -0.08
     Sponge
    -0.08
    POSITIVE LOGITS
    衬衫
    0.10
     wardrobe
    0.10
     purchases
    0.09
    ç©¿æIJŃ
    0.09
    è£ħå¤ĩ
    0.09
    ä¹°çļĦ
    0.09
    ç§ĭåĨ¬
    0.09
    åĽĽåŃ£
    0.09
    è¡£çī©
    0.09
    æĽ¿æį¢
    0.09
    Activations Density 0.063%

    No Known Activations