© 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. 60628
    Prev
    Next
    INDEX
    Explanations

    SQL execution context

    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
    ilon
    -0.10
    éĽĨæĪIJ
    -0.10
    edException
    -0.09
    æŁłæª¬
    -0.09
    笥
    -0.09
    ectomy
    -0.08
    Enumeration
    -0.08
     rh
    -0.08
     Stocks
    -0.08
    enumer
    -0.08
    POSITIVE LOGITS
    没æľīåĬŀæ³ķ
    0.10
    大çIJĨ
    0.09
    ä¸įåģľçļĦ
    0.09
    _extent
    0.09
    ä¹İ
    0.09
     Hick
    0.09
    æĭĦ
    0.09
    éĶµ
    0.09
    åļ¼
    0.08
     Abr
    0.08
    Activations Density 0.150%

    No Known Activations