© 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. 18926
    Prev
    Next
    INDEX
    Explanations

    buildings and infrastructure

    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
     заб
    -0.10
    代è¨Ģ人
    -0.10
    олж
    -0.09
    wahl
    -0.09
     overl
    -0.08
    éĥ¨åĪĨåľ°åĮº
    -0.08
    earn
    -0.08
    Injector
    -0.08
    èĢģå¸Ī们
    -0.08
     оÑģобенно
    -0.08
    POSITIVE LOGITS
    åľ¨éĩĮéĿ¢
    0.11
    è¿ĻéĩĮæĺ¯
    0.10
    设æĸ½å»ºè®¾
    0.09
    建çŃijéĿ¢ç§¯
    0.09
    åħ¥é©»
    0.09
    容纳
    0.09
    ç«ĭéĿ¢
    0.09
    建æĪIJåIJİ
    0.09
    家ä½ı
    0.09
     future
    0.09
    Activations Density 0.235%

    No Known Activations