© 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. 27504
    Prev
    Next
    INDEX
    Explanations

    catalyst, conditions, yield

    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
    rosse
    -0.09
    è¾ľè´Ł
    -0.08
    翻身
    -0.08
    åħ»æĪIJ
    -0.08
    大æĸ¹
    -0.08
    äºĶè¡Į
    -0.08
    äºĮåŃĹ
    -0.08
    é©¿
    -0.08
    cling
    -0.08
    驼
    -0.08
    POSITIVE LOGITS
    绣çŃ¹
    0.10
    éĢļ常æĺ¯
    0.09
    仲
    0.09
    æĬķ
    0.09
     ÙĦتØŃÙĤÙĬÙĤ
    0.09
     ÑĢеак
    0.09
    Ø´ÙĪ
    0.09
    æIJª
    0.09
    åĬ©
    0.09
    sto
    0.09
    Activations Density 0.239%

    No Known Activations