© 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. 39040
    Prev
    Next
    INDEX
    Explanations

    cooking and preparation instructions

    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
    éĹª
    -0.09
    å¥Ķè·ij
    -0.09
    ä¸Ģä¸Ŀ
    -0.08
    unker
    -0.08
    æĢ»å·¥ä¼ļ
    -0.08
     fucked
    -0.08
     badass
    -0.08
    èĬĭ
    -0.08
    çĩĶ
    -0.08
    è·ij
    -0.08
    POSITIVE LOGITS
    é¹³
    0.10
     ÑĤеÑħнологии
    0.09
    ignet
    0.08
     Welch
    0.08
    åĽ½åĨħå¤ĸ
    0.08
    è¹ĭ
    0.08
    éºŁ
    0.08
     lifes
    0.08
    对åŃ©åŃIJ
    0.08
     patented
    0.08
    Activations Density 0.038%

    No Known Activations