© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51455
    Prev
    Next
    INDEX
    Explanations

    received copy or update

    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
    eel
    -0.09
    à¹Ģà¸Ńา
    -0.09
     unseen
    -0.09
    ä¹¾åĿ¤
    -0.08
    ç»Ļåĩº
    -0.08
    èİ·å¾Ĺ
    -0.08
    åĪĨå¼Ģ
    -0.08
    ç»Ļä½ł
    -0.08
    éĢı
    -0.07
    çĿ¢
    -0.07
    POSITIVE LOGITS
    æĿ¥èĩª
    0.11
    ä¾Ĩèĩª
    0.11
    æ´Ĺ礼
    0.11
    éĩĩ访æŶ
    0.11
    æĿ¥èĩªäºİ
    0.10
    ä¸ĢéĿ¢
    0.10
    ä¸Ģå¦Ĥ
    0.10
    è®°èĢħéĩĩ访
    0.10
     notice
    0.09
     Hof
    0.09
    Activations Density 0.236%

    No Known Activations