© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 18040
    Prev
    Next
    INDEX
    Explanations

    garment or clothing items

    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
    æ¶Ī
    -0.10
    çĤ¹äºĨ
    -0.10
    åijķåIJIJ
    -0.10
    éĵ
    -0.10
    鬣
    -0.09
    æĮīä¸ĭ
    -0.09
    精确
    -0.09
    lea
    -0.09
    对ä¸įèµ·
    -0.09
    åįĵè¶Ĭ
    -0.09
    POSITIVE LOGITS
    裤
    0.13
    åĨħè¡£
    0.13
    éŀĭ
    0.12
     trousers
    0.11
    å¤ĸå¥Ĺ
    0.10
    æģ¤
    0.10
    宽æĿ¾
    0.10
    éĿ´
    0.10
    å¥Ĺè£ħ
    0.10
    éŀĭåŃIJ
    0.10
    Activations Density 0.147%

    No Known Activations