© 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. 37476
    Prev
    Next
    INDEX
    Explanations

    setting up or changing components

    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
    èģĤ
    -0.09
    路边
    -0.09
    èĨı
    -0.09
    è¿Ļ个èģĮä¸ļ
    -0.09
    æĿĢäºĨ
    -0.09
    åİŃ
    -0.08
    æĹłæĦı
    -0.08
    éĢĶå¾Ħ
    -0.08
    .tell
    -0.08
    letes
    -0.08
    POSITIVE LOGITS
    éģ®
    0.11
    çĽĸ
    0.10
    顶å±Ĥ设计
    0.09
    ãģ¹ãģį
    0.09
    оÑī
    0.09
    .Validate
    0.09
    oder
    0.08
    åĪ©çī©
    0.08
    jak
    0.08
    å¥Ķæ³¢
    0.08
    Activations Density 0.050%

    No Known Activations