© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 33728
    Prev
    Next
    INDEX
    Explanations

    court panel or division

    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
    家ä½ı
    -0.10
    åĩłåı¥
    -0.10
    å¿ĥ缮ä¸Ń
    -0.10
    hcp
    -0.10
    åIJ»
    -0.10
    çİĭåºľ
    -0.10
    æ°ijæĶ¿
    -0.09
    äº²çľ¼
    -0.09
    Ħ件
    -0.09
    åĩłæŃ¥
    -0.09
    POSITIVE LOGITS
    ÑĥÑĪ
    0.10
    åĴĮå°ļ
    0.08
    绵
    0.08
    ä¼ij
    0.08
    itur
    0.07
     panel
    0.07
    æĺİ亮
    0.07
     rendre
    0.07
    å·ŀ
    0.07
    æī§
    0.07
    Activations Density 0.637%

    No Known Activations