© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52126
    Prev
    Next
    INDEX
    Explanations

    give me

    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
    elman
    -0.10
    é¼»åŃIJ
    -0.10
    许å¤ļ人
    -0.10
    inha
    -0.09
    诣
    -0.09
    åħ¥ä½ı
    -0.09
    泪
    -0.09
    çŃı
    -0.09
    бÑĢа
    -0.09
    大å¤ļæķ°äºº
    -0.08
    POSITIVE LOGITS
     classNames
    0.08
     GAM
    0.08
    acci
    0.08
    æĮģãģ¡
    0.08
    好çļĦ
    0.07
    ouve
    0.07
    åľ¨çĶŁæ´»ä¸Ń
    0.07
    æľĢæĸ°çļĦ
    0.07
     Junk
    0.07
     convergence
    0.07
    Activations Density 0.042%

    No Known Activations