© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36345
    Prev
    Next
    INDEX
    Explanations

    English writer biographies

    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
    Not in Any Lists

    No Comments

    Negative Logits
    线æĿ¡
    -0.10
    讦
    -0.09
    toc
    -0.09
    禧
    -0.09
    ä¼¼ä¹İæĺ¯
    -0.09
     ÑĤоÑĢгов
    -0.09
    å¾IJå·ŀ
    -0.09
    æķ¦
    -0.09
    ç¦ı建
    -0.09
    å½ĵéĢī
    -0.09
    POSITIVE LOGITS
    å°ģ
    0.10
    uele
    0.09
    åĵ²
    0.09
    edList
    0.09
    峡
    0.08
    arus
    0.08
    preter
    0.08
    èı¡
    0.08
    åIJİåı°
    0.08
    äºı
    0.08
    Activations Density 0.048%

    No Known Activations