© 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. 56370
    Prev
    Next
    INDEX
    Explanations

    deciding or making decisions

    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
    误解
    -0.10
    æ¹į
    -0.09
    ìĦ¸
    -0.08
    ç°¿
    -0.08
    æݨçIJĨ
    -0.08
    .jav
    -0.08
    typings
    -0.08
    èĥľåĪ©
    -0.08
    称ä¹ĭ为
    -0.08
    å½Ģ
    -0.08
    POSITIVE LOGITS
    åĨ³å®ļ
    0.21
     deciding
    0.19
    決å®ļ
    0.17
     decide
    0.17
     decides
    0.16
    æĬīæĭ©
    0.16
    åĨ³å®ļäºĨ
    0.16
     whether
    0.14
     decisions
    0.14
    æĺ¯åIJ¦
    0.14
    Activations Density 0.074%

    No Known Activations