© 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. 23530
    Prev
    Next
    INDEX
    Explanations

    actions and descriptions

    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
    neau
    -0.10
    æ´Ĺ礼
    -0.09
    ä¹ŁæĪIJ为
    -0.09
    æĪIJ为ä¸ĢåIJį
    -0.09
    ä¸Ģ个æĸ°çļĦ
    -0.09
    agos
    -0.08
    è¿ĺæľīä¸ĢäºĽ
    -0.08
    ãģ¡ãĤī
    -0.08
    æįİ
    -0.08
    åı¯ä»¥èİ·å¾Ĺ
    -0.08
    POSITIVE LOGITS
    	TokenName
    0.09
    éļıæŶéļıåľ°
    0.09
    ç»Ļ大家
    0.09
    å¾Īé«ĺ
    0.08
    ä¸įåĩºæĿ¥
    0.08
    ç©¿çĿĢ
    0.08
    å¼łæī¬
    0.08
    lems
    0.08
    ĵį
    0.08
    å¾Ĺå¾Ī好
    0.08
    Activations Density 0.079%

    No Known Activations