© 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. 47651
    Prev
    Next
    INDEX
    Explanations

    Apache Software Foundation agreement

    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
    èģĶç½ij
    -0.09
     ta
    -0.08
     Zot
    -0.08
    è¿ĽåŁİ
    -0.08
    ìĭ
    -0.08
    ани
    -0.08
    åħ¨æĹ¥
    -0.08
     superv
    -0.08
    nest
    -0.08
     Pink
    -0.08
    POSITIVE LOGITS
    饼干
    0.10
    ç§ijæĬĢæĪIJæŀľ
    0.09
    çķ¦
    0.09
    åĹĵåŃIJ
    0.09
     Reactive
    0.09
    èĭ¡
    0.09
     пÑĢава
    0.08
    åĸĿäºĨ
    0.08
    èĨĬ
    0.08
    æŁ©
    0.08
    Activations Density 0.351%

    No Known Activations