© 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. 60668
    Prev
    Next
    INDEX
    Explanations

    augmented reality

    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
     shocks
    -0.09
    纣
    -0.09
    äºĮ级
    -0.08
    éĤł
    -0.08
    è¿ĺ羣
    -0.08
    roe
    -0.08
    èѦæĥķ
    -0.08
     Serialize
    -0.08
    èħķ
    -0.08
    çļĦèģĮä¸ļ
    -0.08
    POSITIVE LOGITS
    æī«ä¸Ģæī«
    0.11
    èµ·éĩį
    0.10
    头顶
    0.10
    -overlay
    0.10
    .overlay
    0.09
    aru
    0.09
    overlay
    0.09
    æī«æıı
    0.09
    tons
    0.09
    çľ¼åīį
    0.09
    Activations Density 0.125%

    No Known Activations