© 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. 49842
    Prev
    Next
    INDEX
    Explanations

    duration and time spent

    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
    ç©´
    -0.11
    丰满
    -0.10
    åĮ¹
    -0.10
    å°ļ
    -0.10
    çįŃ
    -0.10
    ä¸ĩåĪĨ
    -0.09
    éĺ¡
    -0.09
     Ending
    -0.09
    è¦ģåİ»
    -0.09
    è¯ĹæĦı
    -0.08
    POSITIVE LOGITS
    åģľçķĻ
    0.14
     duration
    0.12
    æĽĿåħī
    0.11
    Duration
    0.11
    太ä¹ħ
    0.11
     Duration
    0.10
     spent
    0.10
    æļ´éľ²
    0.10
    duration
    0.10
    åīľ
    0.10
    Activations Density 0.111%

    No Known Activations