© 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. 714
    Prev
    Next
    INDEX
    Explanations

    author, performer, presenter

    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
    çľĭå¾Ĺ
    -0.09
    å°±æĪIJäºĨ
    -0.08
    åĪ¹
    -0.08
    Æł
    -0.08
     audi
    -0.08
    chten
    -0.08
     nap
    -0.08
    娣
    -0.08
    侥幸
    -0.08
    éģ¿åŃķ
    -0.08
    POSITIVE LOGITS
    æľ¬äºº
    0.11
     himself
    0.10
    rique
    0.10
    zee
    0.10
    iox
    0.09
    åŀ«
    0.09
    çļĦæĪĺçķ¥
    0.09
    èĵĦ
    0.09
    -engine
    0.08
    less
    0.08
    Activations Density 0.078%

    No Known Activations