© 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. 8440
    Prev
    Next
    INDEX
    Explanations

    mineral trioxide aggregate

    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
    æ¾Ħ
    -0.11
     Flake
    -0.10
    uku
    -0.09
    rimp
    -0.09
     recycle
    -0.09
    åĽŀæĶ¶
    -0.09
    .Xaml
    -0.09
    é²µ
    -0.09
    ibold
    -0.09
     recycling
    -0.08
    POSITIVE LOGITS
    å®®
    0.11
    宫
    0.10
     barr
    0.10
    è¡Ļ
    0.10
    éĥ¢
    0.09
    æīĵä»Ĺ
    0.09
    isten
    0.08
    鸾
    0.08
    åIJĪä¼Ļ人
    0.08
    åħ¥é©»
    0.08
    Activations Density 0.160%

    No Known Activations