© 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. 58428
    Prev
    Next
    INDEX
    Explanations

    seen... an increase

    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
     Cheer
    -0.09
    åĢ¾åIJ¬
    -0.09
    çĴĭ
    -0.09
     اÙĦجÙĩ
    -0.08
    ç»ĻäºĨ
    -0.08
    被æī§è¡Į
    -0.08
    èĢĥèĻijåĪ°
    -0.08
    æĬĹçĸ«
    -0.08
    ä¼ļè®©ä½ł
    -0.08
    å¼Ħå¾Ĺ
    -0.08
    POSITIVE LOGITS
    æīĢæľīæĿĥ
    0.10
    æļ¾
    0.10
    é£İåIJ¹
    0.09
    errat
    0.09
    ä¸įéĶĻçļĦ
    0.09
    ä¸įéĶĻ
    0.08
    ä¸įåı¯æĢĿè®®
    0.08
     Windsor
    0.08
    豫
    0.08
    çªģ
    0.08
    Activations Density 0.035%

    No Known Activations