© 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. 6940
    Prev
    Next
    INDEX
    Explanations

    revenue and money generation

    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
    åºĦ严
    -0.10
    lam
    -0.10
    евиÑĩ
    -0.10
     SPELL
    -0.09
    严å¯Ĩ
    -0.09
    æĪIJéķ¿ä¸º
    -0.09
    picker
    -0.09
    èµı
    -0.09
    ä¸įæĩĪ
    -0.09
    ç½ij讯
    -0.09
    POSITIVE LOGITS
     revenue
    0.10
    Revenue
    0.09
    .Generated
    0.09
    棱
    0.09
     Zw
    0.09
    generated
    0.08
     tripod
    0.08
    æĭįåįĸ
    0.08
    æľīåĬ©äºİ
    0.08
    -generated
    0.08
    Activations Density 0.041%

    No Known Activations