© 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. 682
    Prev
    Next
    INDEX
    Explanations

    in the midst of a process

    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
    uxe
    -0.10
    ä¸Ģæĸ¹
    -0.10
    ä¸Ģçľ¼
    -0.10
    祢
    -0.09
    ä»İä¸ļ
    -0.09
    ASE
    -0.09
    ä¸Ģèĩ´
    -0.09
    thing
    -0.09
    æ²»çĹħ
    -0.08
    /OR
    -0.08
    POSITIVE LOGITS
    大éĩı
    0.10
    ØŃÙħÙĦ
    0.10
    æĪĸå°Ĩ
    0.09
    ä¸įåłª
    0.09
    åį´åıĪ
    0.09
    _DECL
    0.09
    ä»Ģä¹Īæł·
    0.08
    lox
    0.08
    æĿĤçī©
    0.08
    å®£ä¼łæ´»åĬ¨
    0.08
    Activations Density 0.008%

    No Known Activations