© 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. 47617
    Prev
    Next
    INDEX
    Explanations

    foot bone conditions

    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
    egen
    -0.09
    æĢ¥äºİ
    -0.09
    ä¸ī峡
    -0.08
    ä¸ĬåѦ
    -0.08
    _TB
    -0.08
    天çĶŁ
    -0.08
    èIJ½åĪ°å®ŀå¤Ħ
    -0.08
     Vall
    -0.08
    UCE
    -0.08
    -react
    -0.08
    POSITIVE LOGITS
    .mar
    0.09
    oda
    0.09
    åľºåIJĪ
    0.09
    ellen
    0.08
    她说
    0.08
    hair
    0.08
    é£Łçī©
    0.08
    digit
    0.08
     LESS
    0.08
    itizen
    0.08
    Activations Density 0.110%

    No Known Activations