© 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. 60824
    Prev
    Next
    INDEX
    Explanations

    all 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
    足足
    -0.10
    å°½
    -0.09
    åľ¨åIJĮä¸Ģ
    -0.09
    主æĿĥ
    -0.08
    åĬ²
    -0.08
    erc
    -0.08
    OSP
    -0.08
     bgcolor
    -0.08
    è¿Ļåľº
    -0.08
    æ°§
    -0.08
    POSITIVE LOGITS
    æīĭèħķ
    0.11
    åIJĮèĥŀ
    0.10
    èIJĥ
    0.10
    åĮ»ç§ij
    0.10
     Buffered
    0.09
    church
    0.09
    aits
    0.09
    .DisplayMember
    0.09
    ayo
    0.09
    SEQUENTIAL
    0.09
    Activations Density 0.010%

    No Known Activations