© 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. 39096
    Prev
    Next
    INDEX
    Explanations

    education and research

    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
    æķĿ
    -0.09
    SAFE
    -0.09
    endi
    -0.09
    åĿĩ为
    -0.09
    ouns
    -0.08
    æ´ĭæ´ĭ
    -0.08
    工人
    -0.08
    ç¬ijèĦ¸
    -0.08
    çķ¥
    -0.08
    åİŁæľīçļĦ
    -0.08
    POSITIVE LOGITS
    éħ¬
    0.11
    æĸij
    0.10
    nal
    0.09
    á»Ŀ
    0.09
    让æ¶Īè´¹èĢħ
    0.09
    Ø´ÙĨ
    0.08
    èĪ
    0.08
    egg
    0.08
    羦
    0.08
    çŃĸ
    0.08
    Activations Density 0.024%

    No Known Activations