© 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. 6276
    Prev
    Next
    INDEX
    Explanations

    NIH grants and research funding

    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
    ryan
    -0.10
    etro
    -0.09
    ppers
    -0.09
    CISION
    -0.09
    sti
    -0.09
    éĩįçĶŁ
    -0.08
    ä»»æľŁ
    -0.08
    åħļåĴĮæĶ¿åºľ
    -0.08
    orary
    -0.08
    gress
    -0.08
    POSITIVE LOGITS
    容
    0.10
    纵横
    0.09
    plat
    0.09
    éĶ¢
    0.09
    è¯ķçĿĢ
    0.09
    insk
    0.09
    RAL
    0.09
    ility
    0.09
    éªĪ
    0.09
    æĻļ
    0.09
    Activations Density 0.020%

    No Known Activations