© 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. 47405
    Prev
    Next
    INDEX
    Explanations

    biomarkers

    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
    éģı
    -0.09
    严谨
    -0.09
    ourd
    -0.09
    ç¿ĺ
    -0.09
    楷
    -0.09
    INC
    -0.09
    ç§ijå°Ķ
    -0.09
    วาà¸ĩ
    -0.09
    éļ¾æĢª
    -0.08
    ILLS
    -0.08
    POSITIVE LOGITS
     markers
    0.12
     marker
    0.11
    è¯ĬæĸŃ
    0.10
    æłĩå¿Ĺ
    0.10
    診
    0.10
     biom
    0.10
    åĢĻ
    0.10
    çŃĽæŁ¥
    0.09
    markers
    0.09
    æĮĩæłĩ
    0.09
    Activations Density 0.503%

    No Known Activations