© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52096
    Prev
    Next
    INDEX
    Explanations

    organization acronyms

    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
    agr
    -0.09
     Ministry
    -0.09
    ted
    -0.08
    tk
    -0.08
    åĮ»ç§ij
    -0.08
    æĺŁçIJĥ
    -0.08
     favoured
    -0.08
    æĶ¿
    -0.08
    oya
    -0.08
    onders
    -0.08
    POSITIVE LOGITS
    åѦä¼ļ
    0.11
    ä¸ĭå±ŀ
    0.10
    æĹĹä¸ĭçļĦ
    0.10
    æĹĹä¸ĭ
    0.09
     Bowman
    0.09
    å®īåħ¨äºĭæķħ
    0.09
     Convention
    0.09
    Listening
    0.09
    年度
    0.09
    ç¿ł
    0.08
    Activations Density 0.056%

    No Known Activations