© 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. 34883
    Prev
    Next
    INDEX
    Explanations

    official or positional roles

    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
    å½¢å¼ı
    -0.10
    ToolTip
    -0.09
    æ±ģ
    -0.09
    ÑĨеп
    -0.08
    åıĸå¾Ĺ
    -0.08
     formal
    -0.08
    å¤Ħç½ļ
    -0.08
    è´¨éĩıåĴĮ
    -0.08
    讪
    -0.08
    boss
    -0.08
    POSITIVE LOGITS
    uen
    0.09
    èµĦæ·±
    0.09
    亲
    0.09
    裹
    0.09
    æļ¨
    0.09
    ä¸ĢåIJĮ
    0.09
    骨干
    0.09
    ä¹Łæĺ¯éĿŀ常
    0.09
     phá»iji
    0.09
    æĽ¾ä»»
    0.09
    Activations Density 0.130%

    No Known Activations