© 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. 48790
    Prev
    Next
    INDEX
    Explanations

    if ... then

    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
    åĬ¡
    -0.09
    åĭĻ
    -0.09
    峨
    -0.08
     livest
    -0.08
    inke
    -0.08
    ä¸įåĬ¨
    -0.08
    çį²
    -0.08
    èģĶ
    -0.08
    asl
    -0.08
    Sortable
    -0.08
    POSITIVE LOGITS
    è¦ģä¹Ī
    0.10
    澡
    0.10
    ä¼Ļ
    0.09
     вÑģÑıк
    0.09
    æĦıæĢĿæĺ¯
    0.09
     propre
    0.09
    æĢ»é¢Ŀ
    0.08
    ä¸Ģ件äºĭæĥħ
    0.08
    å¤Ħå¤Ħ
    0.08
    æĦıæĢĿ
    0.08
    Activations Density 0.371%

    No Known Activations