© 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. 63850
    Prev
    Next
    INDEX
    Explanations

    names followed by surnames

    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
     gấp
    -0.10
    foil
    -0.09
    Injected
    -0.09
    esk
    -0.09
    _FIFO
    -0.08
    ihn
    -0.08
    æķı
    -0.08
    éĴī
    -0.08
    coding
    -0.08
    _mux
    -0.08
    POSITIVE LOGITS
    ç½
    0.10
     averages
    0.09
    æĦıæĢĿ
    0.09
     averaged
    0.09
    ella
    0.08
    éĤ£ç§į
    0.08
    è¯Ŀ
    0.08
    åħ¥æĪ·
    0.08
    usta
    0.08
    uden
    0.08
    Activations Density 0.150%

    No Known Activations