© 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. 5965
    Prev
    Next
    INDEX
    Explanations

    under his leadership

    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
    Not in Any Lists

    No Comments

    Negative Logits
    heed
    -0.10
    osto
    -0.09
    åĴ«
    -0.08
    éĹª
    -0.08
     Hil
    -0.08
    adin
    -0.08
    åį®
    -0.08
    avin
    -0.08
    ÑĪе
    -0.08
    è¶Ĭé«ĺ
    -0.08
    POSITIVE LOGITS
    åīįä»»
    0.14
    æľŁéĹ´
    0.12
    带é¢Ĩ
    0.12
    çļĦæĪIJ绩
    0.10
    亲èĩª
    0.10
    çļĦ带é¢Ĩ
    0.10
    åľ¨ä»ĸ
    0.10
    æĶ¹åĸĦ
    0.10
    ä¸ļ绩
    0.10
    使å¾Ĺ
    0.10
    Activations Density 0.092%

    No Known Activations