© 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. 33910
    Prev
    Next
    INDEX
    Explanations

    morning activities

    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
    ä»ĬæĻļ
    -0.11
    æļ®
    -0.11
    wine
    -0.10
    _LS
    -0.10
    æĻļé¥Ń
    -0.10
    é»Ħæĺı
    -0.10
     Tonight
    -0.10
    éħ¿
    -0.10
    æĻļä¸Ĭ
    -0.10
     nightly
    -0.10
    POSITIVE LOGITS
    æĹ©é¤IJ
    0.25
    æĻ¨
    0.23
     breakfast
    0.21
    æĹ©æĻ¨
    0.20
     morning
    0.20
     Morning
    0.19
    Morning
    0.19
    æ¸ħæĻ¨
    0.18
     mornings
    0.18
    èµ·åºĬ
    0.18
    Activations Density 0.100%

    No Known Activations