© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 26924
    Prev
    Next
    INDEX
    Explanations

    nymphs, mythology, revels, poetry

    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
    èĪĮ
    -0.09
    çħŀ
    -0.09
    çĻĸ
    -0.08
    åľĪ
    -0.08
    dogs
    -0.08
    åIJŀ
    -0.08
    åĸ»
    -0.08
    çĤĴ
    -0.08
    ä¸įåģľ
    -0.08
     mono
    -0.08
    POSITIVE LOGITS
    欢
    0.11
    欢快
    0.11
    çĭĤ欢
    0.11
    æŃĮèĪŀ
    0.10
    åķ¸
    0.10
    èĬĤå¥ı
    0.10
    她æĺ¯
    0.10
    ä»Ļ女
    0.10
    女ç¥ŀ
    0.10
    éĩİ
    0.10
    Activations Density 0.077%

    No Known Activations