© 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. 19302
    Prev
    Next
    INDEX
    Explanations

    company tickers

    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
    GIN
    -0.09
    è§Ħ磩
    -0.09
    åĪĩåħ¥
    -0.09
    æĿĤçī©
    -0.09
    é¹Ħ
    -0.09
    è¯ħ
    -0.09
    带走
    -0.08
    转ä¼ļ
    -0.08
    ITLE
    -0.08
    sgi
    -0.08
    POSITIVE LOGITS
    为代表çļĦ
    0.10
    éĤ£æł·
    0.10
    dorf
    0.09
    aker
    0.09
    á»ı
    0.08
    å®Į
    0.08
    .setScale
    0.08
    éĩijåĪļ
    0.08
    ä¸ĩèĤ¡
    0.08
    åłª
    0.08
    Activations Density 0.119%

    No Known Activations