© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 59464
    Prev
    Next
    INDEX
    Explanations

    investments in growth

    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
    Negative Logits
    åĩij
    -0.10
    çŃ¹
    -0.09
    äºĴéĢļ
    -0.09
    é¹ij
    -0.09
    utex
    -0.09
    patches
    -0.09
    空
    -0.09
     hollow
    -0.09
    ä¸ĩéĩĮ
    -0.08
    åı¸
    -0.08
    POSITIVE LOGITS
    æĬķèµĦ
    0.20
     investments
    0.19
     investment
    0.18
    çļĦæĬķèµĦ
    0.18
    æĬķè³ĩ
    0.17
    æĬķåħ¥
    0.16
     invest
    0.16
     invested
    0.15
     investing
    0.15
     Investment
    0.15
    Activations Density 0.062%

    No Known Activations