© 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. 39913
    Prev
    Next
    INDEX
    Explanations

    medical advice or terms

    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
    论è¯ģ
    -0.09
    ovsky
    -0.08
    顺çĿĢ
    -0.08
     Bench
    -0.08
    éĴ¢æĿ¿
    -0.07
    åľ¨è¿Ļ
    -0.07
    åħĨ
    -0.07
     ostr
    -0.07
     conj
    -0.07
     Yaz
    -0.07
    POSITIVE LOGITS
    rites
    0.10
    è¾Ľèĭ¦
    0.10
    vertise
    0.10
    ë°±
    0.09
    çĸij
    0.09
    æīįèĥ½
    0.09
    è°¨
    0.09
    /uploads
    0.09
    ä¸ĭå·´
    0.09
    æģ¯æģ¯
    0.09
    Activations Density 0.059%

    No Known Activations