© 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. 6407
    Prev
    Next
    INDEX
    Explanations

    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
     tôn
    -0.10
    æĭĹ
    -0.10
    ä¸Ģç»ı
    -0.09
    è¿Ļ件
    -0.09
    çĭĤ
    -0.09
    ç»ĻæĤ¨
    -0.09
    é«Ń
    -0.09
    å¹ķ
    -0.09
    æĶĢ
    -0.08
    åģļä¸Ģ个
    -0.08
    POSITIVE LOGITS
    èµĭ
    0.11
    åħ³èĬĤ
    0.10
    ÑĮе
    0.09
    èļĮ
    0.09
     arthritis
    0.09
    æ¶Ĥ
    0.09
    SETS
    0.08
    йÑĤ
    0.08
     locom
    0.08
    仲è£ģ
    0.08
    Activations Density 0.378%

    No Known Activations