© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52694
    Prev
    Next
    INDEX
    Explanations

    walk-in

    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
    à¹Į
    -0.10
    ariat
    -0.10
    itecture
    -0.09
    azi
    -0.09
    itect
    -0.09
    ثر
    -0.08
    avr
    -0.08
    jan
    -0.08
    åĽ¾æĸĩ
    -0.08
    ãĤ¢ãĤ¦ãĥĪ
    -0.08
    POSITIVE LOGITS
    zelf
    0.12
    ç²¾ç¥ŀçĹħ
    0.09
    nage
    0.09
    åĢŁçĶ¨
    0.09
    ä¹ŁçŁ¥éģĵ
    0.09
    诨
    0.09
    çĶŁæ´»çļĦ
    0.09
    åĮ»åĬ¡
    0.08
    oly
    0.08
    ção
    0.08
    Activations Density 0.013%

    No Known Activations