© 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. 20658
    Prev
    Next
    INDEX
    Explanations

    technical descriptions and downloads

    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
    ç³ĸæŀľ
    -0.10
    æ·¦
    -0.10
    ëĶķ
    -0.09
    SCR
    -0.09
    ignon
    -0.09
    ãĥĽãĥĨ
    -0.08
    ãĤ¢ãĤ¤ãĥĨ
    -0.08
    LinkId
    -0.08
    ãĤ¿ãĤ¤ãĥŁ
    -0.08
    ayo
    -0.08
    POSITIVE LOGITS
    éĽĴ
    0.09
    ä¹Łä¸įè¦ģ
    0.08
    为主线
    0.08
    ãĢįãĢĮ
    0.08
    çļĦ形象
    0.08
    urally
    0.08
    æĿİåħĪçĶŁ
    0.07
    åīįæıIJæĺ¯
    0.07
    éľĩ
    0.07
    iage
    0.07
    Activations Density 0.456%

    No Known Activations