© 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. 8992
    Prev
    Next
    INDEX
    Explanations

    buy or needed items

    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
    ä¼Ļ
    -0.10
    æݨ广åºĶçĶ¨
    -0.09
    æ¡Į
    -0.09
    _EXIST
    -0.09
    vect
    -0.08
    éķ¶
    -0.08
    æĶ¹è£ħ
    -0.08
     özelli
    -0.08
    ä¸Ĭä¸ĭ游
    -0.08
    æ¼ıæ°´
    -0.08
    POSITIVE LOGITS
    åĽŀæĿ¥
    0.10
    å¿ĥ仪çļĦ
    0.09
    needed
    0.09
    åĽŀ家
    0.09
    åĽłä¸ºä»ĸ
    0.09
    èĩªå·±
    0.08
    以便
    0.08
    å¡«è¡¥
    0.08
    é½IJåħ¨
    0.08
     needed
    0.08
    Activations Density 0.058%

    No Known Activations