© 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. 59224
    Prev
    Next
    INDEX
    Explanations

    proud to be

    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
     мил
    -0.10
    ëĭ¨
    -0.09
    次è¦ģ
    -0.09
    åİĦ
    -0.09
    æķijæµİ
    -0.09
    ÑĤеÑĢ
    -0.09
    ocket
    -0.09
    анг
    -0.09
    ToEnd
    -0.09
    æħĪ
    -0.08
    POSITIVE LOGITS
    éªĦåĤ²
    0.16
    èĩªè±ª
    0.15
     proud
    0.13
     pride
    0.13
     Pride
    0.12
     proudly
    0.10
    OME
    0.09
    å±ŀäºİèĩªå·±
    0.09
    ownt
    0.09
    èĩªä¸»
    0.09
    Activations Density 0.025%

    No Known Activations