© 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. 9497
    Prev
    Next
    INDEX
    Explanations

    enzymes, DNA, burns, acne, fatty acids

    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
     Publi
    -0.08
    åľ¨äº¬
    -0.08
    .keywords
    -0.08
    åĽ½ä¼ļ
    -0.08
    odata
    -0.08
     Sleep
    -0.07
    åĬŁ
    -0.07
    åĤ¬åĮĸåīĤ
    -0.07
    综åIJĪæķ´æ²»
    -0.07
     cleanly
    -0.07
    POSITIVE LOGITS
    èĦļ
    0.10
     MIC
    0.09
    ç½®
    0.09
    æĩĴ
    0.09
    èĤī
    0.09
    èħ³
    0.09
     whirl
    0.09
    isko
    0.08
    对ä»ĺ
    0.08
    åīįåįģ
    0.08
    Activations Density 1.551%

    No Known Activations