© 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. 53337
    Prev
    Next
    INDEX
    Explanations

    millions and billions of dollars

    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
    lya
    -0.10
    å¤©åľ°
    -0.09
    opper
    -0.09
    æĺŁåº§
    -0.09
    صد
    -0.08
    é«ĺä½İ
    -0.08
    å®ı大
    -0.08
     наÑģ
    -0.08
    нÑĮ
    -0.08
     Bra
    -0.08
    POSITIVE LOGITS
    éĢĬ
    0.11
    .tie
    0.09
    ahn
    0.09
    ä¸ĢæĿ¡é¾Ļ
    0.08
    åľ¨èģĮ
    0.08
    ÙĬات
    0.08
    fax
    0.08
    æī«
    0.08
    åıijæĺİ
    0.08
    íĸī
    0.08
    Activations Density 0.010%

    No Known Activations