© 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. 26324
    Prev
    Next
    INDEX
    Explanations

    district states

    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
    OCUS
    -0.10
    éĿĵ
    -0.10
    åı¤ä»Ĭ
    -0.09
     Tamil
    -0.09
    wal
    -0.09
    _IMP
    -0.08
    .pickle
    -0.08
    åŀĥåľ¾
    -0.08
    主人
    -0.08
    èĴ
    -0.08
    POSITIVE LOGITS
    asin
    0.10
    æĭĽ
    0.10
    _ENCOD
    0.09
    è¡ĮæĺŁ
    0.09
    ç£ģ
    0.08
    éļ¶
    0.08
    å»ºåĽ½
    0.08
    ä¸Ńåħ³
    0.08
    ibt
    0.08
     scout
    0.08
    Activations Density 0.652%

    No Known Activations