© 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. 63992
    Prev
    Next
    INDEX
    Explanations

    FT-IR

    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
    hort
    -0.11
    çīĿ
    -0.10
    稿
    -0.09
    -lang
    -0.09
    аÑĤоÑĢ
    -0.09
    hu
    -0.08
    ubit
    -0.08
    bone
    -0.08
     corre
    -0.08
    icates
    -0.08
    POSITIVE LOGITS
    entimes
    0.12
    ening
    0.11
    çĦ¶æĺ¯
    0.11
    羿
    0.10
    佬
    0.10
    øy
    0.10
    说çļĦæĺ¯
    0.10
    ä¸ĬãģĮãĤĬ
    0.09
    .nz
    0.09
    ailing
    0.09
    Activations Density 0.045%

    No Known Activations