© 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. 27733
    Prev
    Next
    INDEX
    Explanations

    steam games, install, optimize

    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
     Decay
    -0.09
    æ°´åĪĨ
    -0.08
    éŃħ
    -0.08
    åģļ大
    -0.08
    鬣
    -0.08
     Playground
    -0.08
    ä¸ĢæĹ¥
    -0.08
    roid
    -0.08
     Banner
    -0.08
    çĭŃçªĦ
    -0.08
    POSITIVE LOGITS
    CHED
    0.10
    ighton
    0.09
    ä¸ŃåĽ½æĸĩåĮĸ
    0.09
    群
    0.09
    æĶ»åĿļ
    0.09
    é¦Ĩ
    0.09
    æ±Ĺ
    0.09
    éĵ³
    0.09
    ç»ĪçĤ¹
    0.09
    สà¸Ļ
    0.09
    Activations Density 0.216%

    No Known Activations