© 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. 6319
    Prev
    Next
    INDEX
    Explanations

    now and currently

    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
    为主è¦ģ
    -0.10
    为éĩįçĤ¹
    -0.08
     ÙĪبعد
    -0.08
    æľīä¸ĢäºĽ
    -0.08
    owie
    -0.08
    åijĪ
    -0.08
    gs
    -0.08
    æľīä¸Ģä½į
    -0.08
    umi
    -0.08
    æĪIJ为
    -0.08
    POSITIVE LOGITS
    ä»Ĭ天
    0.21
    æѤæŶ
    0.20
    æѤåĪ»
    0.18
     ÑģейÑĩаÑģ
    0.17
    æѤæĻĤ
    0.17
    çİ°åľ¨
    0.16
    å¦Ĥä»Ĭ
    0.16
     ÑģегоднÑı
    0.16
    ä»ĬæĹ¥
    0.16
    缮åīįå·²
    0.16
    Activations Density 0.332%

    No Known Activations