© 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. 18480
    Prev
    Next
    INDEX
    Explanations

    renewable energy subsidies and policies

    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
    çĤ¹å¤ļ
    -0.10
    obe
    -0.09
    ç»ıå¼Ģ
    -0.09
    çľģéĴ±
    -0.09
    éħ¥
    -0.09
    åħ¨å¤©
    -0.08
    åľ¨éĩĮéĿ¢
    -0.08
    idia
    -0.08
    .nano
    -0.08
     oslo
    -0.08
    POSITIVE LOGITS
    ä¸įæĺİ
    0.11
    é¼ĵåĬ±
    0.10
    æĭŃ
    0.10
    luet
    0.09
     rap
    0.09
    ä»·åĢ¼è§Ĥ
    0.09
    é¼ĵèĪŀ
    0.09
    论
    0.08
    lix
    0.08
    ç®IJ
    0.08
    Activations Density 0.163%

    No Known Activations