© 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. 21097
    Prev
    Next
    INDEX
    Explanations

    names and titles

    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
    é¦ĸæī¹
    -0.10
    pra
    -0.09
     DAM
    -0.09
    ä¸Ģæĸ¹
    -0.09
    ç½¢
    -0.09
     dam
    -0.08
    ование
    -0.08
    หว
    -0.08
    rol
    -0.08
    åħ¬ä¼Ĺ
    -0.08
    POSITIVE LOGITS
    æ¸į
    0.10
    ä¾Ĺ
    0.10
    鼨
    0.09
    éĻ¬
    0.09
    å°Ķæĸ¯
    0.09
    IDER
    0.09
    èħ´
    0.08
    LERÄ°
    0.08
    ials
    0.08
    ceso
    0.08
    Activations Density 0.002%

    No Known Activations