© 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. 35335
    Prev
    Next
    INDEX
    Explanations

    meanwhile/meantime

    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
    èIJ½ä¸ĭ
    -0.10
    çı©
    -0.09
     Sabb
    -0.09
    ä»İæĿ¥æ²¡
    -0.09
    èIJ½å®ŀ
    -0.09
    bul
    -0.08
    æ¸ħç®Ĺ
    -0.08
    å¾Ĺ罪
    -0.08
    äºĨ好åĩł
    -0.08
    殳
    -0.08
    POSITIVE LOGITS
    çľ¼åīįçļĦ
    0.11
    çľ¼åīį
    0.11
    åľ¨æѤä¹ĭåīį
    0.10
    ãģ¾ãģļãģ¯
    0.10
     meanwhile
    0.10
     meantime
    0.10
    æĢ¥äºİ
    0.10
    æĢ¥
    0.10
    çĥ¦
    0.10
    _already
    0.09
    Activations Density 0.042%

    No Known Activations