© 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. 17412
    Prev
    Next
    INDEX
    Explanations

    gaussian mixture models density estimation

    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
    ä»ĸèĩªå·±
    -0.09
    æĬĬèĩªå·±çļĦ
    -0.09
    pread
    -0.08
    æĶ»åħ³
    -0.08
    è¿Ļ段æŶéĹ´
    -0.08
    åħ¨åŁŁ
    -0.08
    HandlerContext
    -0.08
    æ³®
    -0.08
    è·Ľ
    -0.08
     whistle
    -0.08
    POSITIVE LOGITS
    æĽ´æĸ°
    0.09
    å°ĺ
    0.09
    åĭī
    0.09
    ä¼łæĦŁ
    0.09
    åĪĨå¸ĥåľ¨
    0.09
     æĽ´æĸ°
    0.09
    çıł
    0.09
     marginalized
    0.09
    åĪĨå¸ĥ
    0.08
    çijĽ
    0.08
    Activations Density 0.251%

    No Known Activations