© 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. 29395
    Prev
    Next
    INDEX
    Explanations

    word fragments for names

    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
    abyrinth
    -0.10
    æݧ
    -0.10
    burgh
    -0.09
    à¹Ģหà¸Ļ
    -0.09
    ocs
    -0.09
    Ñģло
    -0.09
    loses
    -0.09
     Filed
    -0.09
    åŃº
    -0.09
    igor
    -0.08
    POSITIVE LOGITS
    ä¸İåħ¶
    0.09
    âĢŀ
    0.08
    磨
    0.08
    åįłçĶ¨
    0.08
    ä¸įåİ»
    0.08
     Dup
    0.08
    ueur
    0.08
    çĥ¦
    0.08
    宪
    0.08
    èĨĽ
    0.08
    Activations Density 0.007%

    No Known Activations