© 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. 16528
    Prev
    Next
    INDEX
    Explanations

    probable, likely, eventual

    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
    tin
    -0.10
    æĢ¨
    -0.09
    alte
    -0.09
    echa
    -0.09
    åħļåĴĮ
    -0.09
    åľ¨åĽ½å¤ĸ
    -0.09
    .jump
    -0.09
    åľ¨ä¸ĢæĹģ
    -0.08
    æľķ
    -0.08
    æ·Ģ
    -0.08
    POSITIVE LOGITS
     eventual
    0.09
    hood
    0.09
    çīĪæĿĥ声æĺİ
    0.09
    shed
    0.08
    èģĶ缣
    0.08
    itudes
    0.08
    NCY
    0.08
    ãģĹãģı
    0.08
    çīĸ
    0.08
    verts
    0.08
    Activations Density 0.011%

    No Known Activations