© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 21618
    Prev
    Next
    INDEX
    Explanations

    definition of "

    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
    æ³ķåĪĻ
    -0.09
    å¤Ķ
    -0.08
    æĢ§è´¨
    -0.08
    çļĦ妻åŃIJ
    -0.08
    çļĦå°ı
    -0.08
    ç»Ļå®Ŀå®Ŀ
    -0.08
    ç»Ļèĩªå·±
    -0.08
    çļĦèĦ¸
    -0.08
    ä¹Ŀé¾Ļ
    -0.08
    åŃ¦æł¡çļĦ
    -0.08
    POSITIVE LOGITS
    è¿Ļ个è¯į
    0.12
     Bren
    0.10
    åĩŃä»Ģä¹Ī
    0.09
    滨
    0.09
    iage
    0.09
    åįķè¯į
    0.09
    èľķåıĺ
    0.09
    .oc
    0.08
    è¿Ŀ竳
    0.08
    宾客
    0.08
    Activations Density 0.168%

    No Known Activations