© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36306
    Prev
    Next
    INDEX
    Explanations

    hip replacement patients with osteoarthritis

    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
    ooth
    -0.12
    å³Ĵ
    -0.09
    æľĪåĪĿ
    -0.09
    åĨĻçĿĢ
    -0.09
    èĩªæŁ¥
    -0.09
    FML
    -0.09
     мн
    -0.09
    å·¡è§Ĩ
    -0.09
    ä¼ĹæīĢ
    -0.09
    身åŃIJ
    -0.08
    POSITIVE LOGITS
     MISS
    0.10
    让æĤ¨
    0.09
     sym
    0.09
    åºŀ
    0.09
    èIJ½
    0.08
    鸡
    0.08
    ä¹¾åĿ¤
    0.08
    éĩį度
    0.08
    è¡°
    0.08
     Miss
    0.08
    Activations Density 0.427%

    No Known Activations