© 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. 26726
    Prev
    Next
    INDEX
    Explanations

    civic leaders and community organizations

    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
     Ministry
    -0.09
    åįĥéĩĮ
    -0.09
    åݻ买
    -0.09
     flame
    -0.09
    emade
    -0.08
    绾
    -0.08
    åĽ½éĺ²éĥ¨
    -0.08
    幺
    -0.08
    æĬ¥å¤į
    -0.08
    åĩ¹
    -0.08
    POSITIVE LOGITS
    æ¢Ń
    0.12
    ä¼ģä¸ļ家
    0.11
    åķĨ人
    0.10
    ç»ħ
    0.10
    amat
    0.10
    åIJĦçķĮ
    0.10
    å®ŀä¸ļ
    0.10
    å¥łåŁº
    0.09
    åĴĭ
    0.09
    èĢĨ
    0.09
    Activations Density 0.163%

    No Known Activations