© 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. 12390
    Prev
    Next
    INDEX
    Explanations

    notice of intent or adoption

    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
    æį®æѤ
    -0.13
    çģ¯åħī
    -0.09
    çĻ½ç³ĸ
    -0.09
    è°¤
    -0.09
    è¢ĸ
    -0.09
    å½ĵåľ°æĶ¿åºľ
    -0.09
    çľ¼æ³ª
    -0.09
    磼
    -0.09
    æŃ¤åŁºç¡Ģä¸Ĭ
    -0.09
     ÙĦدÙĬ
    -0.09
    POSITIVE LOGITS
     intent
    0.10
    intent
    0.09
    Intent
    0.09
     potential
    0.08
    æĦıåIJij
    0.08
     Meng
    0.08
    abouts
    0.08
     change
    0.08
    è¿Ļä¸ĢçĤ¹
    0.08
     presence
    0.08
    Activations Density 0.023%

    No Known Activations