© 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. 24247
    Prev
    Next
    INDEX
    Explanations

    system/router/system/monitors

    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
    åĮºåĨħ
    -0.08
    æģº
    -0.08
    涤
    -0.08
    éķ¿å®ī
    -0.08
    éĩįçĤ¹é¢ĨåŁŁ
    -0.08
    arch
    -0.08
    andard
    -0.08
    ross
    -0.08
     пÑĢедмеÑĤ
    -0.08
    obre
    -0.07
    POSITIVE LOGITS
    _attached
    0.10
    çħĮ
    0.10
    åıĸè¯ģ
    0.09
    .QueryString
    0.09
    çļ¿
    0.09
    eration
    0.09
    两款
    0.09
    æ¥Ķ
    0.08
    çıłæ±Ł
    0.08
    setDisplay
    0.08
    Activations Density 0.189%

    No Known Activations