© 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. 9224
    Prev
    Next
    INDEX
    Explanations

    would have or would otherwise

    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
    åĬ¡
    -0.11
    rlen
    -0.10
    æĭŁ
    -0.09
    å¿ĥæĦ¿
    -0.08
    åħ¬ä¸»
    -0.08
    æĵ¬
    -0.08
    梯
    -0.08
    .Len
    -0.08
    æľĢæĸ°çļĦ
    -0.08
    æĻĵå¾Ĺ
    -0.08
    POSITIVE LOGITS
    igu
    0.09
    åĵī
    0.09
    èĢĮæĺ¯
    0.09
    ä¸įçĦ¶
    0.09
    æĬ¥åºŁ
    0.08
    ì´Į
    0.08
    ogui
    0.08
    æģIJæĢķ
    0.08
    wares
    0.08
    ennen
    0.08
    Activations Density 0.029%

    No Known Activations