© 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. 52318
    Prev
    Next
    INDEX
    Explanations

    state of standing

    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
    illis
    -0.10
    oser
    -0.09
    åŁĭ
    -0.09
    çľ¼åħī
    -0.09
    æīĭ
    -0.09
    èĭ¦æģ¼
    -0.09
    odef
    -0.09
    lander
    -0.09
    gien
    -0.09
    ÙĬض
    -0.08
    POSITIVE LOGITS
    à¹ģà¸ļà¸ļ
    0.10
     pragma
    0.09
    æķĸ
    0.09
     <![
    0.08
    森
    0.08
    bane
    0.08
     Fur
    0.08
    åĽĽæĺ¯
    0.08
    åħ¨æ°ij
    0.08
    è¿Ľåİ»
    0.08
    Activations Density 0.024%

    No Known Activations