© 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. 54884
    Prev
    Next
    INDEX
    Explanations

    economics and related fields

    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
    æķĪçĽĬ
    -0.08
    åįıåķĨ
    -0.08
    è¯
    -0.08
    çĽijè§Ĩ
    -0.08
    ç§ijåѦåıijå±ķ
    -0.08
    ç½ijç»ľä¼łæĴŃ
    -0.08
    æ¦ľæł·
    -0.08
    éĽī
    -0.08
    ntp
    -0.07
    ewise
    -0.07
    POSITIVE LOGITS
    ç»ıæµİåѦ
    0.14
    ç»ıæµİåŃ¦å®¶
    0.13
    å®ıè§Ĥç»ıæµİ
    0.12
     economists
    0.12
     Econ
    0.11
     econ
    0.10
     styl
    0.10
     economist
    0.10
     firms
    0.10
    åĪ»çĶ»
    0.10
    Activations Density 0.161%

    No Known Activations