© 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. 19553
    Prev
    Next
    INDEX
    Explanations

    evaluation of worth or recognition

    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
    éªĦ
    -0.09
    éĹ²ç½®
    -0.09
    æ·¡æ·¡çļĦ
    -0.09
    пад
    -0.09
    pad
    -0.09
    ä½łæĥ³
    -0.09
    åĴĦ
    -0.09
    ç¿Ķ
    -0.08
     Babe
    -0.08
    èĦIJ
    -0.08
    POSITIVE LOGITS
    å¾Ĺä¸įåĪ°
    0.10
    à¸Ļà¸Ńà¸ģ
    0.09
    ä¸Ģçīĩ
    0.09
     Nacional
    0.09
    æ¸ł
    0.08
    å¤ļåIJĥ
    0.08
     underrated
    0.08
    æ¹ĸåĮĹ
    0.08
    å«¡
    0.08
    å¸Ĥåľºä»½é¢Ŀ
    0.08
    Activations Density 0.039%

    No Known Activations