© 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. 55322
    Prev
    Next
    INDEX
    Explanations

    prevent from happening

    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
    è¿Ļæł·æīįèĥ½
    -0.10
    ise
    -0.09
     kend
    -0.09
    æĪIJ绩
    -0.09
    飧
    -0.09
    åıªè§ģ
    -0.09
    ãģĬãģĭãģĴ
    -0.09
    诣
    -0.08
    äºĭå®ŀ
    -0.08
    æīĭèħķ
    -0.08
    POSITIVE LOGITS
    æľīä»»ä½ķ
    0.13
     being
    0.12
    åĭ¿
    0.10
    ä½ĵçİ°åĩº
    0.10
    åĮ¡
    0.10
    æĪIJ为
    0.10
     tá»ĵn
    0.10
    åľ¨ä»Ĭå¹´
    0.09
    æĪIJ为ä¸Ģ个
    0.09
    æĹ©æĹ¥
    0.09
    Activations Density 0.039%

    No Known Activations