© 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. 33524
    Prev
    Next
    INDEX
    Explanations

    organic matter decomposition

    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
    è°¨
    -0.09
    UED
    -0.09
     stag
    -0.08
    openh
    -0.08
    ä¹ı
    -0.08
    å¹ķ
    -0.08
    èĭĽ
    -0.08
    kie
    -0.08
    China
    -0.08
    å¾Ĵ
    -0.08
    POSITIVE LOGITS
    åľŁå£¤
    0.12
     soil
    0.10
    itta
    0.10
    æľīæľº
    0.10
    åľ¾
    0.10
    ä¿®åħ»
    0.10
    èĤ¥æĸĻ
    0.10
    åħ»èĤ²
    0.09
    æ²ĥ
    0.09
    涵
    0.09
    Activations Density 0.044%

    No Known Activations