© 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. 9390
    Prev
    Next
    INDEX
    Explanations

    what it does

    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
     oci
    -0.08
    Ø¡
    -0.08
    perial
    -0.08
    èĩªçĦ¶èĢĮçĦ¶
    -0.08
    æµij
    -0.08
     millennium
    -0.08
     soak
    -0.08
    æĬĺ
    -0.07
    èĬŃ
    -0.07
    ç´«èī²
    -0.07
    POSITIVE LOGITS
    inand
    0.10
    ãģĤãĤĮ
    0.10
    çľĭçĤ¹
    0.09
    ãģ£ãģ¡ãĤĥ
    0.09
    æĮĩæľĽ
    0.09
    æĸ°æĪ¿
    0.09
    äºĭåĦ¿
    0.09
     Jarvis
    0.09
    åİ¢
    0.09
    èĥ¸åīį
    0.09
    Activations Density 0.120%

    No Known Activations