© 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. 26991
    Prev
    Next
    INDEX
    Explanations

    integral part of team/organization

    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
    .ak
    -0.09
    æºħ
    -0.09
    äºĭå®ŀä¸Ĭ
    -0.09
    æ·¹
    -0.08
    èģĮä¸ļ
    -0.08
    çļĦèģĮä¸ļ
    -0.08
    å½¼æѤ
    -0.08
    оÑĢм
    -0.08
    主æĮģ
    -0.08
     Bew
    -0.08
    POSITIVE LOGITS
    ä¸įåı¯æĪĸ缺
    0.11
    ç¼¢
    0.09
    æ¦ľ
    0.09
    æ£ĭ
    0.08
    .strategy
    0.08
    å¿ħä¸įåı¯å°ij
    0.08
    çĸij
    0.08
    èĬĤèĥ½åĩıæİĴ
    0.08
    帷
    0.08
    èµ·
    0.08
    Activations Density 0.023%

    No Known Activations