© 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. 51544
    Prev
    Next
    INDEX
    Explanations

    names ending in "y" or "n", followed by comma or proper noun

    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
    äºĶå®ĺ
    -0.09
    åIJĮåŁİ
    -0.09
    åģļ人
    -0.09
    CN
    -0.09
    足以
    -0.08
    讳
    -0.08
    å§ĭ
    -0.08
    enty
    -0.08
    è¡Į人
    -0.08
    unting
    -0.08
    POSITIVE LOGITS
    olk
    0.10
    æĸĽ
    0.09
    ISTER
    0.09
    ÙĦÙĩ
    0.09
    åĨĴ
    0.09
    éĢ
    0.09
    .esp
    0.08
    æ¡ĤèĬ±
    0.08
    èħĶ
    0.08
    æ¯Ľ
    0.08
    Activations Density 0.001%

    No Known Activations