© 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. 603
    Prev
    Next
    INDEX
    Explanations

    chemical suffixes

    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
    åĿª
    -0.09
    éĤ£ä¸ªæŶåĢĻ
    -0.08
    åĤ¨éĩı
    -0.08
    ographical
    -0.08
    åijĬè¯īä»ĸ
    -0.08
    gage
    -0.08
    ä¸įä¼ļæľī
    -0.08
    èĤĵ
    -0.08
    blo
    -0.08
     Redistributions
    -0.08
    POSITIVE LOGITS
    olla
    0.10
    磼
    0.09
    åĬ¨æijĩ
    0.09
    çIJĨäºĭ
    0.09
    å©´
    0.08
    uga
    0.08
    uez
    0.08
     Resident
    0.08
    .bitmap
    0.08
    æ¯ı次éĥ½
    0.08
    Activations Density 0.051%

    No Known Activations