© 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. 34727
    Prev
    Next
    INDEX
    Explanations

    brand new

    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
    éļĶçĿĢ
    -0.10
    è´®
    -0.09
    æīĭæ³ķ
    -0.09
    å¾Īå¥½åľ°
    -0.09
    çĶļ
    -0.08
    apter
    -0.08
    åŁİå¸Ĥ建设
    -0.08
    èĬĿåĬł
    -0.08
    责令
    -0.08
    èĢĥèĻijåĪ°
    -0.08
    POSITIVE LOGITS
    æĸ°çļĦ
    0.38
     new
    0.33
    æĸ°ãģĹãģĦ
    0.27
    à¹ĥหม
    0.27
     mỼi
    0.26
     новÑĭй
    0.25
     ìĥĪë¡ľìļ´
    0.25
     нового
    0.24
    ä¸Ģ个æĸ°çļĦ
    0.24
     новÑĭÑħ
    0.24
    Activations Density 0.212%

    No Known Activations