© 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. 3581
    Prev
    Next
    INDEX
    Explanations

    trade imbalance

    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
    rika
    -0.10
    å¥ij
    -0.09
    å¼ĢèįĴ
    -0.09
    æĻ®
    -0.08
    ç¡IJ
    -0.08
    å¼Ģä¸ļ
    -0.08
    æĹĹèĪ°åºĹ
    -0.08
    çł
    -0.08
    PATH
    -0.08
    iva
    -0.08
    POSITIVE LOGITS
    å¤ĸæ±ĩ
    0.15
    è¿Ľåı£
    0.11
    åĩºåı£
    0.10
    è´¸æĺĵ
    0.10
    失
    0.10
    imports
    0.10
    è¿Ľåĩºåı£
    0.09
     export
    0.09
     imports
    0.09
    æµ·åħ³
    0.09
    Activations Density 0.031%

    No Known Activations