© 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. 29827
    Prev
    Next
    INDEX
    Explanations

    delivery, deployment, release, update, launch

    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
    éĻIJè´Ń
    -0.10
    æĺİçıł
    -0.09
    è´¥
    -0.09
    å¿ĥ头
    -0.09
    çĶľçĶľ
    -0.09
    èį¸
    -0.09
    ä¼ĺè¶Ĭ
    -0.09
    çĶ¨èĩªå·±çļĦ
    -0.08
    æķĹ
    -0.08
    éģ¿
    -0.08
    POSITIVE LOGITS
    ä¸įæħİ
    0.12
    ä¸Ĭ线
    0.12
    é¢ijç¹ģ
    0.10
     release
    0.10
    .release
    0.09
     delivery
    0.09
    é¢ijé¢ij
    0.09
     releasing
    0.09
    æ»ļ
    0.09
    é¢ijçİĩ
    0.09
    Activations Density 0.089%

    No Known Activations