© 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. 16563
    Prev
    Next
    INDEX
    Explanations

    demon, power, present

    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
    éĹ·
    -0.10
    æĪIJçĨŁ
    -0.10
    è¡Įäºĭ
    -0.10
    æĪIJçĨŁçļĦ
    -0.10
    æĤ²ä¼¤
    -0.09
    è¯Ĺè¯į
    -0.09
    åĽŀæĥ³
    -0.09
    奶
    -0.09
     Kauf
    -0.09
    æŨ
    -0.09
    POSITIVE LOGITS
    åħ«å¹´
    0.09
    å¥ĩ迹
    0.09
    碣
    0.08
     Carey
    0.08
    æĬķ
    0.08
    åħįç¨İ
    0.08
    çĸĹ
    0.08
    æĸ¥
    0.08
    ven
    0.08
    æĴ¤
    0.08
    Activations Density 0.133%

    No Known Activations