© 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. 23951
    Prev
    Next
    INDEX
    Explanations

    people followed by descriptive words

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ites
    -0.08
    æĬ¥ä¸ļ
    -0.08
    maf
    -0.08
    éĤ´
    -0.08
    éļĻ
    -0.08
    ibil
    -0.08
    åħŃåIJĪ
    -0.07
     happy
    -0.07
    ema
    -0.07
    .setError
    -0.07
    POSITIVE LOGITS
    /pub
    0.10
    åī©ä¸ĭ
    0.09
    aight
    0.09
    chie
    0.09
    为æѤ
    0.09
    à¹īา
    0.09
    kir
    0.09
    åľ¨ä¹İ
    0.09
    askan
    0.08
    омеÑĢ
    0.08
    Activations Density 0.025%

    No Known Activations