© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 4718
    Prev
    Next
    INDEX
    Explanations

    managed resources or services

    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
    tems
    -0.09
    ials
    -0.09
    骤
    -0.08
     اÙĦÙħÙĦ
    -0.08
    祯
    -0.08
    ç½ħ
    -0.08
    tal
    -0.08
     thinner
    -0.08
    综åIJĪåĪ©çĶ¨
    -0.08
    зÑĭ
    -0.08
    POSITIVE LOGITS
    ä¸ĵ人
    0.11
    åĢĮ
    0.10
    ä¹ĭä¸Ń
    0.10
    ä¸į顾
    0.10
     Disclaimer
    0.09
    çĬĬ
    0.09
    åįĩèµ·
    0.09
    è¡°éĢĢ
    0.09
    åįĹåĮĹ
    0.09
    主義
    0.09
    Activations Density 0.038%

    No Known Activations