© 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. 6202
    Prev
    Next
    INDEX
    Explanations

    money in millions

    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
    nice
    -0.09
    ESS
    -0.09
    edian
    -0.09
    好è¿IJ
    -0.08
    å¯Įè´µ
    -0.08
    nesia
    -0.08
    âĺŀ
    -0.08
    èĻ¿
    -0.08
    ä¼ģä¸ļæıIJä¾Ľ
    -0.08
    微信åı·
    -0.08
    POSITIVE LOGITS
    :///
    0.10
    çĵ·
    0.09
    ç¼Ķ
    0.08
    ç«ł
    0.08
    pell
    0.08
    èµ·èįī
    0.08
     protagonist
    0.08
    åIJĿ
    0.08
    WithOptions
    0.08
    æŀ«
    0.08
    Activations Density 0.032%

    No Known Activations