© 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. 12439
    Prev
    Next
    INDEX
    Explanations

    facts about

    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
    deep
    -0.09
    æĮĩ导ä¸ĭ
    -0.08
     intercepted
    -0.08
    odelist
    -0.08
    sn
    -0.08
    wed
    -0.08
    ç«ĭä½ĵ
    -0.08
    æĸ°ä¸Ģè½®
    -0.08
    LocalizedString
    -0.08
    iero
    -0.08
    POSITIVE LOGITS
    äºĭå®ŀ
    0.31
     facts
    0.31
    çļĦäºĭå®ŀ
    0.30
    facts
    0.24
     ÑĦакÑĤ
    0.22
    å®ŀäºĭ
    0.21
    äºĭ實
    0.20
     Facts
    0.20
    _fact
    0.19
     ÑĦак
    0.18
    Activations Density 0.039%

    No Known Activations