© 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. 2216
    Prev
    Next
    INDEX
    Explanations

    eco-friendly or environmentally friendly

    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
    ertz
    -0.11
    读æĩĤ
    -0.11
    线ä¸Ĭ线ä¸ĭ
    -0.10
    adol
    -0.10
    æĹ¥å¸¸å·¥ä½ľ
    -0.10
    ijn
    -0.09
    à¸Ńà¸ģ
    -0.09
    eton
    -0.09
    ãĥijãĥ¼
    -0.09
    esses
    -0.08
    POSITIVE LOGITS
    绿èī²çݯä¿Ŀ
    0.17
    çݯä¿Ŀ
    0.15
    èĬĤèĥ½åĩıæİĴ
    0.12
    ä½İ碳
    0.12
    绿èī²
    0.11
    èĬĤ约
    0.10
    èĬĤèĥ½
    0.10
    åºŁ
    0.10
    èĬĤèĥ½çݯä¿Ŀ
    0.10
    綳
    0.10
    Activations Density 0.089%

    No Known Activations