© 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. 16592
    Prev
    Next
    INDEX
    Explanations

    motions / point / gun / deal

    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
     deÄŁerl
    -0.09
    ulaire
    -0.09
     Plaza
    -0.08
    ÒĴ
    -0.08
    黯
    -0.08
    etal
    -0.08
    outh
    -0.08
     kaldı
    -0.08
    _flutter
    -0.08
    ä¸ĢåĪĨéĴ±
    -0.08
    POSITIVE LOGITS
    æį»
    0.11
    åĨķ
    0.10
    çĶŁæ´»è´¨éĩı
    0.09
    没äºĨ
    0.09
    emap
    0.09
    åį°
    0.08
    èĢĮéĿŀ
    0.08
    æĴ·
    0.08
    åĪ°æľĢåIJİ
    0.08
     icing
    0.08
    Activations Density 0.010%

    No Known Activations