© 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. 24315
    Prev
    Next
    INDEX
    Explanations

    film titles and names

    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
    éªĬ
    -0.10
     Meghan
    -0.10
    æĭ±
    -0.09
     gi
    -0.09
    ä¾Ľåħ»
    -0.09
    äºĴ缸
    -0.09
    çī¹éķ¿
    -0.09
    å´©
    -0.09
     Forever
    -0.08
    åIJij社ä¼ļ
    -0.08
    POSITIVE LOGITS
     lean
    0.08
    à¹Į
    0.08
    çłĶ
    0.08
    ugin
    0.08
    广çĶµ
    0.08
    æĪij们å°Ĩ
    0.08
     Execution
    0.08
    sl
    0.08
    èĨı
    0.08
    èĥĸåŃIJ
    0.08
    Activations Density 0.070%

    No Known Activations