© 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. 35456
    Prev
    Next
    INDEX
    Explanations

    sports statistics

    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
    åĪĥ
    -0.09
     Wr
    -0.09
    çĶµè§Ĩæľº
    -0.09
    éĴŀ
    -0.09
    ACHI
    -0.09
    å®ļåIJij
    -0.09
    æĪª
    -0.08
    ResourceManager
    -0.08
    åĮ£
    -0.08
    å±Ĥåĩº
    -0.08
    POSITIVE LOGITS
    人åĬĽ
    0.10
     Intelli
    0.09
    æŃ»åİ»
    0.09
    樽
    0.09
    è¿Ļ个èģĮä¸ļ
    0.09
    ç³Ł
    0.08
    à¹ģยà¸ģ
    0.08
    循
    0.08
    è¨Ģ论
    0.08
     brew
    0.08
    Activations Density 0.090%

    No Known Activations