© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 59274
    Prev
    Next
    INDEX
    Explanations

    game levels and stages

    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
    Negative Logits
    æµİ
    -0.09
     пед
    -0.09
     ped
    -0.09
    享
    -0.09
     ÑģоÑģÑĤоÑıние
    -0.08
    åģİ
    -0.08
    æĮļ
    -0.08
    SURE
    -0.08
     ÑįнеÑĢги
    -0.08
    Ped
    -0.08
    POSITIVE LOGITS
    æīĵè¿Ľ
    0.10
    è¿Ļä¸ĢåĪ»
    0.09
    .ToDouble
    0.09
    å¤Ħç½®
    0.09
    è¿ĻäºĽéĹ®é¢ĺ
    0.09
    æĪIJè´¥
    0.09
    ç©´
    0.08
    微软
    0.08
    åĩĨæŶ
    0.08
    èĢĥéªĮ
    0.08
    Activations Density 0.041%

    No Known Activations