© 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. 59194
    Prev
    Next
    INDEX
    Explanations

    vice president

    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
    è·ijéģĵ
    -0.09
    å®ľ
    -0.09
    isse
    -0.08
    仵
    -0.08
    æı£
    -0.08
    ä¸įè¦ģ太
    -0.08
    æĹ©ä¸Ĭ
    -0.08
     shelves
    -0.08
    æĢģ
    -0.08
    inea
    -0.07
    POSITIVE LOGITS
    ç»ıçIJĨ
    0.14
    .Manager
    0.11
     manager
    0.10
    主管
    0.10
    andel
    0.10
    åijĺ
    0.10
    erview
    0.10
    _vp
    0.10
    (manager
    0.09
    åºIJ
    0.09
    Activations Density 0.061%

    No Known Activations