© 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. 9124
    Prev
    Next
    INDEX
    Explanations

    preferring or suggesting something

    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
    undy
    -0.09
    çļĦç¾İ好
    -0.08
    rå
    -0.08
    ä¸ĢæŶ
    -0.08
     Verd
    -0.08
    æľĢæĹ©
    -0.08
     Correct
    -0.07
    å¯Ħ
    -0.07
    {Name
    -0.07
    éĢł
    -0.07
    POSITIVE LOGITS
    ãĤĤãģ£ãģ¨
    0.14
    èİ·å¾ĹæĽ´å¤ļ
    0.12
    æ¯Ķå¦Ĥ说
    0.11
    æĽ´å¤ļçļĦ
    0.11
     ÑħоÑĤÑı
    0.10
    åı¯ä»¥æĽ´å¥½
    0.10
    å¤ļåIJĥ
    0.10
    ä¾ĭå¦Ĥ
    0.10
    为ä»Ģä¹Īä¸į
    0.10
    å°±èĥ½å¤Ł
    0.10
    Activations Density 0.080%

    No Known Activations