© 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. 634
    Prev
    Next
    INDEX
    Explanations

    none

    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
    ä¸ĢèĪ¬äºº
    -0.10
    æŁIJç§į
    -0.10
    sWith
    -0.10
    éĩijå±±
    -0.10
    asan
    -0.10
    wards
    -0.09
    æĢ§å¼º
    -0.09
    ãģıãĤĮ
    -0.09
    æŁIJä¸Ģ
    -0.09
    æŁIJ
    -0.09
    POSITIVE LOGITS
    ê¹IJ
    0.11
    place
    0.10
    /all
    0.10
    ergy
    0.10
    OfString
    0.09
    åı¯æĥ³
    0.09
    -too
    0.09
    jang
    0.09
    izr
    0.09
    arty
    0.09
    Activations Density 0.031%

    No Known Activations