© 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. 939
    Prev
    Next
    INDEX
    Explanations

    degree abbreviations

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ£
    -0.09
    é¹Ĭ
    -0.09
    失信
    -0.09
     Barth
    -0.08
     dif
    -0.08
    luent
    -0.08
    itz
    -0.08
    åŃļ
    -0.08
    éĴĪ对æĢ§
    -0.08
     Shirley
    -0.08
    POSITIVE LOGITS
    æĸ°å½¢åĬ¿
    0.09
    ált
    0.09
    KER
    0.08
     Jur
    0.08
    çĤ¹çĤ¹å¤´
    0.08
    åıªæľīä¸Ģ个
    0.08
    rait
    0.08
    饽
    0.08
    æĬĦ
    0.08
    æĪij们éĥ½
    0.08
    Activations Density 0.020%

    No Known Activations