© 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. 12354
    Prev
    Next
    INDEX
    Explanations

    connecting different concepts

    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
    ä¸įåıĬ
    -0.10
    çľ¼æ³ª
    -0.10
    ingen
    -0.09
    éĵĽ
    -0.09
    imestamp
    -0.09
    åįģéĩĮ
    -0.09
    odal
    -0.09
    ë§Ŀ
    -0.09
    æĢħ
    -0.09
    ccount
    -0.09
    POSITIVE LOGITS
    quot
    0.08
    WithString
    0.08
     simply
    0.08
     ld
    0.08
    ld
    0.08
    à¸Ńà¸ļ
    0.08
    jit
    0.08
    è´¸æĺĵ
    0.08
    yn
    0.07
     meteor
    0.07
    Activations Density 0.223%

    No Known Activations