© 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. 47641
    Prev
    Next
    INDEX
    Explanations

    project management

    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
    oya
    -0.11
    èĩªåįij
    -0.10
    oyer
    -0.09
    åį¤
    -0.09
    人æ°ij群ä¼Ĺ
    -0.09
    宵
    -0.09
    erral
    -0.09
    ä¹Ŀæ±Ł
    -0.09
    佬
    -0.09
    inue
    -0.09
    POSITIVE LOGITS
    é¡¹çĽ®ç»ıçIJĨ
    0.12
    .Project
    0.11
    project
    0.10
    é¡¹çĽ®
    0.09
     project
    0.09
     Project
    0.09
    antt
    0.09
    é¡¹çĽ®çļĦ
    0.09
    çijľ
    0.09
    Project
    0.08
    Activations Density 0.097%

    No Known Activations