© 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. 3034
    Prev
    Next
    INDEX
    Explanations

    responsibilities and operations

    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
    èĤĦ
    -0.09
    .mods
    -0.09
    æĸĩåĮĸåºķèķ´
    -0.09
    OptionsResolver
    -0.09
    .dense
    -0.09
    ersion
    -0.09
    ä¼ij
    -0.09
    èĸ¨
    -0.09
    éĢĿä¸ĸ
    -0.09
    portun
    -0.08
    POSITIVE LOGITS
    è¿Ļéĥ¨åĪĨ
    0.12
    èģĮèĥ½
    0.12
    主ä½ĵ责任
    0.11
    å¤ĸåĮħ
    0.11
    éĩįä»»
    0.11
    交ç»Ļ
    0.11
     responsibilities
    0.10
    èģĮè´£
    0.10
    éĥ¨åĪĨ
    0.10
     responsibility
    0.10
    Activations Density 0.100%

    No Known Activations