© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53387
    Prev
    Next
    INDEX
    Explanations

    nobility titles

    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
    ä¸Ńåħ³
    -0.10
    天涯
    -0.09
    çªĿ
    -0.09
    èĩªä¹ł
    -0.08
    pod
    -0.08
     thi
    -0.08
    0
    -0.08
    æĭĹ
    -0.08
    ju
    -0.08
    è¯ģæĺİ
    -0.08
    POSITIVE LOGITS
    çĪµ
    0.11
    伯
    0.09
    åħ¼
    0.09
    ä¸Ģ个éĹ®é¢ĺ
    0.09
    éĦĤ
    0.09
    们çļĦ
    0.09
    åĴĮ社ä¼ļ
    0.08
    æīĢæıIJä¾Ľ
    0.08
    ä¼ģä¸ļåıijå±ķ
    0.08
    èIJ¥ä¸ļ
    0.08
    Activations Density 0.027%

    No Known Activations