© 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. 21738
    Prev
    Next
    INDEX
    Explanations

    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
    鼶è·Ŀ离
    -0.09
    太å°ij
    -0.08
    ä¸Ģå°ı
    -0.08
    太ä¹ħ
    -0.08
    èĽ®
    -0.08
     rec
    -0.08
    éľľ
    -0.08
    ç§ij室
    -0.08
    inte
    -0.08
     pig
    -0.08
    POSITIVE LOGITS
    åľ¨è·¯ä¸Ĭ
    0.10
    æĶ¿çŃĸæݪæĸ½
    0.10
    ervo
    0.10
     billions
    0.10
    ä¿Ŀå§Ĩ
    0.10
    åºŀ大çļĦ
    0.09
    ervoir
    0.09
    é«ĺéĢŁå¢ŀéķ¿
    0.09
    .mit
    0.09
    ä¸ĩ亿åħĥ
    0.09
    Activations Density 0.056%

    No Known Activations