© 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. 12329
    Prev
    Next
    INDEX
    Explanations

    Casey, Lyle W. Cayce

    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
    yard
    -0.09
    å¤©åľ°
    -0.09
    itech
    -0.09
    å¼¢
    -0.09
    æĦı義
    -0.08
    产ä¸ļåĮĸ
    -0.08
    lex
    -0.08
    æ®ĸæ°ij
    -0.08
    è¯Ĥ
    -0.08
    icer
    -0.08
    POSITIVE LOGITS
    kir
    0.11
    hood
    0.09
    ites
    0.09
    ingle
    0.09
    rogen
    0.09
    ÙĬØ¡
    0.09
    rame
    0.09
    rior
    0.09
    lic
    0.09
    ness
    0.09
    Activations Density 0.003%

    No Known Activations