© 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. 26280
    Prev
    Next
    INDEX
    Explanations

    simulation and analysis

    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
    èĬĿ麻
    -0.08
    atom
    -0.07
    ʲ
    -0.07
    æ±Łå±±
    -0.07
    å¾¼
    -0.07
    æĮģä¹ħ
    -0.07
    hoe
    -0.07
    Detect
    -0.07
    身份
    -0.07
    纬
    -0.07
    POSITIVE LOGITS
    ä»¿çľŁ
    0.10
     ÑĢаÑģÑĩеÑĤ
    0.09
     Solver
    0.09
     simulation
    0.09
     param
    0.08
    çłĶ究
    0.08
    顾éĹ®
    0.08
    åīĸ
    0.08
     solver
    0.08
     Simulation
    0.08
    Activations Density 0.404%

    No Known Activations