© 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. 29454
    Prev
    Next
    INDEX
    Explanations

    numbers followed by "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
    令
    -0.09
    бан
    -0.09
    ä¸ĢèĦļ
    -0.09
    lsen
    -0.09
    篡
    -0.08
    çł¥
    -0.08
     cupboard
    -0.08
    å¤Ħå¤Ħ
    -0.08
    aren
    -0.08
     robber
    -0.08
    POSITIVE LOGITS
    åĮ¡
    0.11
    åĽ´è§Ĥ
    0.11
    缼ä¼ļ
    0.10
    åıĤåĬłä¼ļè®®
    0.10
    åĪ°åľº
    0.10
    ç«ĻçĿĢ
    0.10
    ä½Ļ人
    0.09
    åĩºåĬ¨
    0.09
    èģļéĽĨ
    0.09
    izr
    0.09
    Activations Density 0.107%

    No Known Activations