© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 26256
    Prev
    Next
    INDEX
    Explanations

    other side of

    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
    Negative Logits
    åIJ¯
    -0.09
    2
    -0.09
    3
    -0.09
    1
    -0.09
    AndGet
    -0.09
    5
    -0.08
    6
    -0.08
    upp
    -0.08
    0
    -0.08
    4
    -0.08
    POSITIVE LOGITS
    åı¦ä¸Ģè¾¹
    0.15
    éĤ£è¾¹
    0.13
    尽头
    0.13
    å½¼
    0.11
     Theodore
    0.10
    ä¸Ģ头
    0.10
    对éĿ¢
    0.10
    æµĨ
    0.09
     bên
    0.09
    à¸Ľà¸¥à¸²à¸¢
    0.09
    Activations Density 0.051%

    No Known Activations