© 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. 63815
    Prev
    Next
    INDEX
    Explanations

    sweets, jellies, and chewy treats

    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
    Not in Any Lists

    No Comments

    Negative Logits
    nt
    -0.08
    ion
    -0.08
     nguyá»ĩn
    -0.08
    NT
    -0.08
    éĴ¼
    -0.08
    IfExists
    -0.08
    çī©èģĶç½ij
    -0.08
    å¾Īéĩįè¦ģ
    -0.08
    é»Ħéĩij
    -0.08
    ture
    -0.07
    POSITIVE LOGITS
    æĢ»é¢Ŀ
    0.10
    IRD
    0.10
    icious
    0.09
    åĿļ飧
    0.09
    лаÑģ
    0.09
    icles
    0.09
    ITLE
    0.09
    éĽı
    0.09
    uze
    0.09
    亲
    0.09
    Activations Density 0.047%

    No Known Activations