© 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. 27927
    Prev
    Next
    INDEX
    Explanations

    kitchenware or tableware

    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
    íıIJ
    -0.09
    alyzer
    -0.09
    CHA
    -0.09
    éra
    -0.09
    ä¸Ģç§į
    -0.08
    atem
    -0.08
    reib
    -0.08
    gba
    -0.08
    ä¸Ģ举
    -0.08
    _TA
    -0.08
    POSITIVE LOGITS
    åĭº
    0.11
    ture
    0.09
    æĮĸæİĺ
    0.09
    stalk
    0.09
    çŃ·
    0.09
    åĿļ强
    0.09
    ä¸įäºĨ
    0.08
    é¤IJåħ·
    0.08
    åĨµ
    0.08
    æģº
    0.08
    Activations Density 0.007%

    No Known Activations