© 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. 63954
    Prev
    Next
    INDEX
    Explanations

    nominated for awards

    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
    åģĩæľŁ
    -0.10
    iron
    -0.09
     agreed
    -0.08
    à¸ŀวà¸ģ
    -0.08
     Hir
    -0.08
    èĩªå¸¦
    -0.08
     agre
    -0.07
    æĻ®åıĬ
    -0.07
    æĥļ
    -0.07
    ì¤Ħ
    -0.07
    POSITIVE LOGITS
    æĦŁåĬ¨
    0.11
    çĥŁçģ«
    0.10
    æıIJåIJį
    0.10
    åĢĻéĢī
    0.10
    .bs
    0.10
    åĴĮåľ°åĮº
    0.09
    nex
    0.09
    骥
    0.09
     Bellev
    0.09
    æľĢä½³
    0.09
    Activations Density 0.027%

    No Known Activations