© 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. 63844
    Prev
    Next
    INDEX
    Explanations

    what i am doing"}

    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
    rastructure
    -0.10
    friendly
    -0.09
    èİİ
    -0.08
    afort
    -0.08
    éĩįæŀĦ
    -0.08
    ker
    -0.08
    ÑĪа
    -0.08
     اÙĦبÙĨ
    -0.08
    æĭ¢
    -0.08
     завод
    -0.08
    POSITIVE LOGITS
    åģļçļĦäºĭ
    0.09
    æ¸İ
    0.09
    ibal
    0.09
    åģļçļĦ
    0.09
    ãĤ¹ãĤŃ
    0.09
    é¦ĸåħĪæĺ¯
    0.08
    é¦ģ
    0.08
     ÑģлÑĥÑĩ
    0.08
     overly
    0.08
    ç»ıåİĨ
    0.08
    Activations Density 0.022%

    No Known Activations