© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20651
    Prev
    Next
    INDEX
    Explanations

    unannounced, spontaneous, initiative

    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
    reuse
    -0.11
    çľ¼çľĭ
    -0.09
    rovers
    -0.09
    uish
    -0.09
    èĸ®
    -0.09
    _PAGES
    -0.09
    íĨµ
    -0.09
    iode
    -0.08
    utura
    -0.08
    roid
    -0.08
    POSITIVE LOGITS
    åĢ¡è®®
    0.10
    æ¼²
    0.10
     disclaimer
    0.09
    åĨĴåĩº
    0.09
    主åĬ¨
    0.09
    主åĭķ
    0.08
     grouped
    0.08
    omatic
    0.08
    æ³¼
    0.08
    ä¹Ŀé¾Ļ
    0.08
    Activations Density 0.011%

    No Known Activations