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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21737
    Prev
    Next
    INDEX
    Explanations

    economic development, significance, success

    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
    æĭĴ
    -0.10
    hare
    -0.09
    -covered
    -0.08
    åĩĿ
    -0.08
    çł
    -0.08
    åħ¬çĽĬ
    -0.08
    биÑĢ
    -0.08
    积æ·Ģ
    -0.08
    ARIANT
    -0.08
    raham
    -0.08
    POSITIVE LOGITS
    å®ŀæĥł
    0.10
    èµ·é£ŀ
    0.09
    ÙĬات
    0.09
    åĮĿ
    0.09
    æĸ°å¸¸æĢģ
    0.09
    åĴĮ社ä¼ļ
    0.09
    éħ¥
    0.09
    å¼ĢåıijåĮº
    0.09
     naked
    0.09
    åįķ纯çļĦ
    0.09
    Activations Density 0.051%

    No Known Activations