© 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. 60836
    Prev
    Next
    INDEX
    Explanations

    common function words and articles

    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
    æī¿
    -0.09
    å¸Ľ
    -0.09
    _TICK
    -0.09
    åIJ¹
    -0.09
    .Serial
    -0.09
    ä¸Ģæľ¬
    -0.09
    chal
    -0.09
    ä¸Ńå¤ĸ
    -0.09
     Permanent
    -0.09
    ails
    -0.09
    POSITIVE LOGITS
    æľĢåIJİä¸Ģ个
    0.11
    è¦ģåĬłå¼º
    0.09
    oug
    0.08
    çĸĨ
    0.08
    æľĢåIJİ
    0.08
    unge
    0.08
    лаÑģÑĤ
    0.08
    MF
    0.08
    ä¸¥æł¼çļĦ
    0.08
     Gaming
    0.08
    Activations Density 0.308%

    No Known Activations