© 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. 23512
    Prev
    Next
    INDEX
    Explanations

    suffixes like -based, -themed

    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
    ä¼ĹæīĢ
    -0.11
    æŃ£åĵģ
    -0.10
    大éĿ¢ç§¯
    -0.10
    OfType
    -0.10
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.10
    容è²Į
    -0.10
    è´¨éĩıåĴĮ
    -0.09
    ä¹ħ
    -0.09
    ä¸ķ
    -0.09
    æĦıæĢĿæĺ¯
    -0.09
    POSITIVE LOGITS
    -themed
    0.10
    ophile
    0.08
    -friendly
    0.08
    ida
    0.08
    -oriented
    0.08
    é¢ĺæĿIJ
    0.08
    缸åºĶçļĦ
    0.08
    omat
    0.08
    æĦıè¯Ĩ
    0.08
    ulous
    0.08
    Activations Density 0.662%

    No Known Activations