© 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. 10474
    Prev
    Next
    INDEX
    Explanations

    trading and financial markets

    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
    redd
    -0.09
    èģĶç³»æĪij们
    -0.09
    满满çļĦ
    -0.09
    天河
    -0.08
    æĹłä¸į
    -0.08
    atom
    -0.08
    æľīæĿĥ
    -0.08
    hood
    -0.08
    rus
    -0.08
    èĭį
    -0.08
    POSITIVE LOGITS
    缺å¸Ń
    0.10
    zik
    0.10
    _BUS
    0.09
    åĩºåħ¥å¢ĥ
    0.09
    èĪ
    0.08
    çĺ¾
    0.08
    åŁİ乡
    0.08
    æĹ¶æľº
    0.08
    åįij
    0.08
    åıijå±ķæĪĺçķ¥
    0.08
    Activations Density 0.022%

    No Known Activations