© 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. 16671
    Prev
    Next
    INDEX
    Explanations

    partridge, Artemisinin, neolithic, neonatal

    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
    éĤ¸
    -0.11
    åĴĮåľ°åĮº
    -0.11
    §è¡Į
    -0.10
    æł·çļĦ
    -0.10
    éĹ³
    -0.09
    Ø°ÙĬ
    -0.09
    usal
    -0.09
    LayoutPanel
    -0.09
    ç»ıåħ¸çļĦ
    -0.09
     pk
    -0.09
    POSITIVE LOGITS
     Scient
    0.09
     kort
    0.09
    æĢĿ绪
    0.08
    vinc
    0.08
    اÙģÙĤ
    0.08
    achable
    0.08
    _CPP
    0.08
    æĶĢ
    0.08
    è¾£
    0.08
     Scene
    0.08
    Activations Density 0.006%

    No Known Activations