© 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. 49832
    Prev
    Next
    INDEX
    Explanations

    process and task management

    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
    桶
    -0.10
    åĪ»
    -0.10
    çŃĴ
    -0.09
    大äºĭ
    -0.09
    æħ¨
    -0.09
    \TestCase
    -0.09
    æĥ³è¿ĩ
    -0.09
    主æĦı
    -0.09
    è¿ĩå¾Ĺ
    -0.08
    å±ħ室
    -0.08
    POSITIVE LOGITS
     PID
    0.10
    PID
    0.10
    	pid
    0.10
    (Process
    0.10
    è¿Ľç¨ĭ
    0.09
    两家
    0.09
    pid
    0.09
     processes
    0.09
     running
    0.09
    æĺŁ
    0.09
    Activations Density 0.155%

    No Known Activations