© 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. 38581
    Prev
    Next
    INDEX
    Explanations

    mining and farming

    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
    swith
    -0.10
    æĸ°ä¸ī
    -0.10
    leness
    -0.09
    èĮĦ
    -0.09
    对å¤ĸå¼ĢæĶ¾
    -0.09
    REST
    -0.08
     Xxx
    -0.08
     شأÙĨ
    -0.08
    .Automation
    -0.08
     Tenn
    -0.08
    POSITIVE LOGITS
    æĮĸæİĺ
    0.16
    æİĺ
    0.12
    åıijæİĺ
    0.10
    ä»İä¸Ń
    0.09
    æ´Ļ
    0.09
    mdl
    0.09
    主åĬ¨
    0.09
    å·²ä¹ħ
    0.09
    æıIJçĤ¼
    0.09
    æºŁ
    0.08
    Activations Density 0.034%

    No Known Activations