© 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. 26024
    Prev
    Next
    INDEX
    Explanations

    chart position

    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
    BAD
    -0.09
    rades
    -0.09
    eof
    -0.09
    áŀķ
    -0.09
    cade
    -0.08
    åĶ±æŃĮ
    -0.08
    è¿ĵ
    -0.08
    жд
    -0.08
     BAD
    -0.08
    scan
    -0.08
    POSITIVE LOGITS
    à¹Į
    0.10
    ãģĿãģĨãģª
    0.09
     Anthem
    0.09
    é³Į
    0.09
    owe
    0.09
    ori
    0.08
    åīįåįģ
    0.08
    DMI
    0.08
    鸳
    0.08
    顶å°ĸ
    0.08
    Activations Density 0.004%

    No Known Activations