© 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. 10651
    Prev
    Next
    INDEX
    Explanations

    money, games, properties

    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
    çĪIJ
    -0.09
    çłº
    -0.09
    æľīåĬ©
    -0.09
    çijĻ
    -0.08
    æīĵå¾Ĺ
    -0.08
    çļĦèĥ½åĬĽ
    -0.08
    çĤī
    -0.08
    çķı
    -0.08
    è°Īèµ·
    -0.08
     Belg
    -0.08
    POSITIVE LOGITS
    unc
    0.10
    -prefix
    0.10
    ä»Ļ女
    0.09
    è¿ĺåİŁ
    0.09
    unta
    0.09
    车çīĮ
    0.09
    大佬
    0.08
     اÙĦعÙħ
    0.08
     Slee
    0.08
    EventHandler
    0.08
    Activations Density 0.199%

    No Known Activations