© 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. 32066
    Prev
    Next
    INDEX
    Explanations

    highest quality

    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
    å¾Ī好çļĦ
    -0.10
    èįª
    -0.10
    å¾Īæĥ³
    -0.10
    ä»Ļ
    -0.10
    éĿŀ常好
    -0.09
    æľĢæĹ©çļĦ
    -0.09
    å¾Ī强
    -0.09
    çĸ£
    -0.08
    å¾Īé«ĺçļĦ
    -0.08
    å¤ļå°ij
    -0.08
    POSITIVE LOGITS
    èĩªä¸»
    0.10
    uze
    0.10
     Leh
    0.09
    éģ£
    0.09
    iglia
    0.09
    ÙĬات
    0.09
    ’B
    0.09
    й
    0.09
    ë°¸
    0.09
    审议
    0.08
    Activations Density 0.026%

    No Known Activations