© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 59179
    Prev
    Next
    INDEX
    Explanations

    hospitalizations and admissions

    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
    Negative Logits
     поÑĤеÑĢ
    -0.09
    atology
    -0.08
    ä»İä¸ļ人åijĺ
    -0.08
    ä»İä¸ļèĢħ
    -0.08
    à¤ĺ
    -0.07
    丸
    -0.07
    cludes
    -0.07
    at
    -0.07
    ide
    -0.07
     ext
    -0.07
    POSITIVE LOGITS
     wegen
    0.14
    æĺ¯åĽłä¸º
    0.14
    å°±æĺ¯åĽłä¸º
    0.13
    åĽłä¸ºä½ł
    0.13
    åĽł
    0.12
    åĽłä¸ºå¥¹
    0.12
    åĽłä¸º
    0.12
    åĽłä¸ºä»ĸ们
    0.12
    åĽłä¸ºä»ĸ
    0.12
    ÙĬز
    0.11
    Activations Density 0.268%

    No Known Activations