© 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. 16778
    Prev
    Next
    INDEX
    Explanations

    office and management positions

    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
    uf
    -0.09
    æĢ¿
    -0.09
    ych
    -0.09
    locs
    -0.09
    InternalServerError
    -0.08
    æ°ij主åħļ
    -0.08
     Dems
    -0.08
    mma
    -0.08
    æŃ¤äºº
    -0.08
     TERM
    -0.08
    POSITIVE LOGITS
    åīĥ
    0.10
    æ¦Ī
    0.10
    è¡·
    0.09
    tre
    0.09
    iso
    0.09
    éĹ¾
    0.09
    å®ī举
    0.08
    禧
    0.08
    é¹Ń
    0.08
    第ä¸ī代
    0.08
    Activations Density 0.006%

    No Known Activations