© 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. 62284
    Prev
    Next
    INDEX
    Explanations

    real estate investing

    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
    è´¯éĢļ
    -0.11
    ofil
    -0.09
    éĽĨä¸Ńåľ¨
    -0.09
    åľ¨ç½ijä¸Ĭ
    -0.09
    é¢Ĭ
    -0.09
    æ´ĭ
    -0.09
    åħ¬åħ±åį«çĶŁ
    -0.09
    æľįåĬ¡æ°´å¹³
    -0.09
    æĶ»åħ³
    -0.09
    丧
    -0.09
    POSITIVE LOGITS
    åĽŀæĬ¥
    0.15
    å¢ŀåĢ¼
    0.14
    æĬķèµĦ
    0.14
    çļĦæĬķèµĦ
    0.12
    çIJĨè´¢
    0.12
     investment
    0.12
     returns
    0.12
    æĶ¶çĽĬçİĩ
    0.11
    æĬķè³ĩ
    0.11
     investing
    0.11
    Activations Density 0.061%

    No Known Activations