© 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. 623
    Prev
    Next
    INDEX
    Explanations

    read on

    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
    å¼ķ
    -0.09
    åıĹä¸įäºĨ
    -0.09
    åľ¨åĵªéĩĮ
    -0.08
    åıįè¿ĩæĿ¥
    -0.08
    à¸Ĺาà¸ĩ
    -0.08
    å¥Ĺè·¯
    -0.08
    à¸Ļำมา
    -0.08
     recip
    -0.08
    à¸Ńà¸Ńà¸ģมา
    -0.08
    ì§ĵ
    -0.08
    POSITIVE LOGITS
    éĢĭ
    0.11
    éĹ³
    0.09
    ä¸ĭåİ»
    0.09
    eka
    0.08
    åĽ½éĻħåĮĸ
    0.08
    å¾Ģä¸ĭ
    0.08
    claimer
    0.08
    anax
    0.08
    ä¸ĭéĿ¢
    0.08
    etically
    0.08
    Activations Density 0.015%

    No Known Activations