© 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. 48305
    Prev
    Next
    INDEX
    Explanations

    ways to make food

    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
    æĦŁ
    -0.12
    æľī人
    -0.11
    线ä¸ĭ
    -0.09
    墨
    -0.08
    æľīäºĽäºº
    -0.08
     orm
    -0.08
    æİ°
    -0.08
    è¿ĩåİ»äºĨ
    -0.08
    Sizes
    -0.08
    _study
    -0.08
    POSITIVE LOGITS
    åģļåĩº
    0.12
    æĶ¶æĭ¾
    0.11
    çĥ¹é¥ª
    0.10
    OMEM
    0.10
    åģļé¥Ń
    0.10
    çĥ¹
    0.10
    åħħå®ŀ
    0.10
    æļ¹
    0.09
    æ¯Ķäºļ
    0.09
    çļĦåģļæ³ķ
    0.09
    Activations Density 0.115%

    No Known Activations