© 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. 12280
    Prev
    Next
    INDEX
    Explanations

    Freedom of Information Act

    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
     bidi
    -0.10
    æİĬ
    -0.09
    å¸
    -0.09
    ½æķ°
    -0.09
    ego
    -0.08
    å¸Ŀ
    -0.08
    RANDOM
    -0.08
    ä½łè¿ĺ
    -0.08
    bib
    -0.08
    лик
    -0.08
    POSITIVE LOGITS
    heimer
    0.10
    æĸĹ
    0.09
    æ²ī积
    0.09
    ibly
    0.09
    æĿ²
    0.08
    .Attributes
    0.08
    วล
    0.08
    .twitch
    0.08
    neau
    0.08
    USA
    0.08
    Activations Density 0.009%

    No Known Activations