© 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. 63975
    Prev
    Next
    INDEX
    Explanations

    Shakespeare and authors

    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
    esto
    -0.09
    leur
    -0.09
     Arbor
    -0.09
    orary
    -0.09
    æĥħåĨµè¿Ľè¡Į
    -0.09
    shell
    -0.08
    rong
    -0.08
     Newsp
    -0.08
    éĥijå·ŀ
    -0.08
    ç¼£
    -0.08
    POSITIVE LOGITS
    ian
    0.11
    ium
    0.10
    emu
    0.09
    éĻ¢éķ¿
    0.09
    æĸĽ
    0.09
    yard
    0.09
    stad
    0.08
    hire
    0.08
    peare
    0.08
    ernal
    0.08
    Activations Density 0.004%

    No Known Activations