© 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
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20360
    Prev
    Next
    INDEX
    Explanations

    temporal markers or durations

    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
    æĽĻ
    -0.10
    æĪªæŃ¢
    -0.10
    æĪªèĩ³
    -0.10
    æĺ¯ä»Ģä¹Īåij¢
    -0.10
    æĪIJç«ĭäºİ
    -0.10
     Bauer
    -0.09
    è¿Ļæł·çļĦè¯Ŀ
    -0.09
    åĩºçĤī
    -0.09
    æ²»çIJĨä½ĵç³»
    -0.09
     оÑĤзÑĭв
    -0.09
    POSITIVE LOGITS
    ä¹Łå°±æĺ¯
    0.11
    æŃ£å¥½
    0.11
     coinc
    0.09
    æŃ£æĺ¯
    0.09
    ä¹ŁæŃ£æĺ¯
    0.08
     BT
    0.08
    æģ°å¥½
    0.08
    nte
    0.07
    olon
    0.07
    usp
    0.07
    Activations Density 0.094%

    No Known Activations