© 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. 64114
    Prev
    Next
    INDEX
    Explanations

    eventually, someday, before negative outcomes

    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
    å«Įçĸij
    -0.10
    æĺ¼
    -0.10
    ä¸ĢåŃĹ
    -0.09
    åįĬ天
    -0.09
    çľ¼ç¥ŀ
    -0.09
    çĨ¨
    -0.09
    é¡¿æŶ
    -0.08
    ç«ŁçĦ¶
    -0.08
    ä¸Ģæīĭ
    -0.08
    blr
    -0.08
    POSITIVE LOGITS
    æī¾ä¸ª
    0.10
    è¦ģä¹Ī
    0.10
    åĪ°æŶåĢĻ
    0.10
    Either
    0.10
    æĺİå¹´
    0.10
     someday
    0.10
     Eventually
    0.10
    æĽ´æ·±
    0.10
    éĨĴ
    0.09
     sooner
    0.09
    Activations Density 0.053%

    No Known Activations