© 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. 22451
    Prev
    Next
    INDEX
    Explanations

    past experiences contrasted with present

    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
    èĮ«èĮ«
    -0.09
    è¦ģä¸įè¦ģ
    -0.09
    主é¢ĺæ´»åĬ¨
    -0.09
    æ±Łæ·®
    -0.08
    对äºİæĪij们
    -0.08
    vl
    -0.08
    忽
    -0.08
    å¿ĥ仪
    -0.08
    æī§æĦı
    -0.08
    ç»Īäºİ
    -0.08
    POSITIVE LOGITS
    èµ·çłģ
    0.14
    ä½Ĩçİ°åľ¨
    0.12
    èĢĮçİ°åľ¨
    0.12
    éĤ£æŶåĢĻ
    0.12
    éĤ£æŶ
    0.11
    èĩ³å°ij
    0.11
    agon
    0.09
    åķĸ
    0.09
    æīª
    0.09
    .Today
    0.09
    Activations Density 0.166%

    No Known Activations