© 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. 20689
    Prev
    Next
    INDEX
    Explanations

    sell-off, short-term

    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
    ìĤ´
    -0.10
    yps
    -0.10
    aring
    -0.09
    rus
    -0.09
    ration
    -0.09
    olan
    -0.09
    lay
    -0.08
    æīİ
    -0.08
    ally
    -0.08
    uate
    -0.08
    POSITIVE LOGITS
    ä»ħ代表
    0.09
    æĸ¹åIJij
    0.08
    èĽĶ
    0.08
     intermitt
    0.08
    æīª
    0.08
    è¦ģ害
    0.08
    å¿ĥå¾Ĺ
    0.08
    èĢķ
    0.08
    åī¡
    0.08
    agr
    0.08
    Activations Density 0.006%

    No Known Activations