© 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. 40404
    Prev
    Next
    INDEX
    Explanations

    freshly/recently/newly + past participle

    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
    ig
    -0.09
    åĩŃ
    -0.09
    æľ«
    -0.08
    amo
    -0.08
     IG
    -0.08
     thinker
    -0.08
    æĭ£
    -0.08
    éĢ¼
    -0.08
    staking
    -0.08
    å°ıå·§
    -0.08
    POSITIVE LOGITS
    aments
    0.09
    rollers
    0.09
    æĭĽåij¼
    0.09
    é«ĺçļĦ
    0.09
    ãģ¨ãģª
    0.09
    满满çļĦ
    0.09
    æı¡ä½ı
    0.09
    sted
    0.08
    /root
    0.08
     Humb
    0.08
    Activations Density 0.002%

    No Known Activations