© 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. 29671
    Prev
    Next
    INDEX
    Explanations

    glucose storage, uptake, synthesis, metabolism

    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
    bay
    -0.09
    neau
    -0.08
    éĩĮç¨ĭ
    -0.08
    EG
    -0.08
    认
    -0.08
    ç»ĪçĤ¹
    -0.08
    æĿı
    -0.08
    æ¦ľæł·
    -0.08
    å·´
    -0.07
    MessageType
    -0.07
    POSITIVE LOGITS
    转åĮĸ为
    0.15
    åĤ¨åŃĺ
    0.12
    å½ĵä½ľ
    0.12
    åĤ¨
    0.11
    转åĮĸ
    0.11
    _STORAGE
    0.10
    代谢
    0.10
    å½ĵåģļ
    0.10
     storage
    0.10
    转æį¢
    0.10
    Activations Density 0.078%

    No Known Activations