© 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. 780
    Prev
    Next
    INDEX
    Explanations

    web addresses and git repositories

    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
    åįģäºĮäºĶ
    -0.14
     Flickr
    -0.13
     iPod
    -0.12
    éĩijèŀįåį±æľº
    -0.10
    Yahoo
    -0.10
     Wii
    -0.10
    ç»ĻåĬĽ
    -0.10
    ç§ijåѦåıijå±ķ
    -0.10
     BlackBerry
    -0.10
     XHTML
    -0.10
    POSITIVE LOGITS
    èµĭèĥ½
    0.12
    å®ĺ宣
    0.11
     vscode
    0.11
    .jupiter
    0.10
    纪å§ĶçĽijå§Ķ
    0.10
    èİ·å¾ĹæĦŁ
    0.10
    飧æĢ§
    0.10
    .kotlin
    0.10
    åĬłæĮģ
    0.10
    .grpc
    0.10
    Activations Density 4.914%

    No Known Activations