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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21118
    Prev
    Next
    INDEX
    Explanations

    follow-up care

    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
    æīĢèĩ´
    -0.10
    lator
    -0.09
    åľ¨æİ¥åıĹ
    -0.09
    åĩĨå¤ĩ好
    -0.08
     Sham
    -0.08
    ائÙĦ
    -0.08
    è¿ŀå¤ľ
    -0.08
    åĿı
    -0.08
    ãĥĹãĥ©ãĤ¤
    -0.08
    æŁľåı°
    -0.08
    POSITIVE LOGITS
    è·Łè¿Ľ
    0.15
    åIJİç»Ń
    0.14
    åĶ®åIJİ
    0.14
    è·Łè¸ª
    0.12
     ongoing
    0.12
    继ç»Ń
    0.12
    æĮģç»Ń
    0.12
    追踪
    0.11
     post
    0.10
    ä¿Ŀä¿®
    0.10
    Activations Density 0.071%

    No Known Activations