© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 4976
    Prev
    Next
    INDEX
    Explanations

    customer income

    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
    off
    -0.11
    åIJĮä¸ļ
    -0.09
    åĮºåŁŁåĨħ
    -0.09
    ä¸Ģåı·
    -0.09
    åķĸ
    -0.09
    ussels
    -0.08
    纳æĸ¯
    -0.08
    Ùģت
    -0.08
    æ¬łç¼º
    -0.08
    åģİ
    -0.08
    POSITIVE LOGITS
    æħĿ
    0.09
     اÙĦساعة
    0.09
    顶å±Ĥ
    0.09
    æĦŁäºº
    0.08
    .valueOf
    0.08
    enqueue
    0.08
    è¦ģ好好
    0.08
    /output
    0.08
    åĮ»çĶ¨
    0.08
    æ¯ĶæĪij
    0.08
    Activations Density 0.023%

    No Known Activations