© 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. 33988
    Prev
    Next
    INDEX
    Explanations

    judicial district court

    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
     Leigh
    -0.10
    èįIJ
    -0.09
    ãģĬåĭ§ãĤģ
    -0.09
     sle
    -0.08
     Alam
    -0.08
    èµ°ä¸Ĭ
    -0.08
    çķ¦
    -0.08
    é¬Ī
    -0.08
    жа
    -0.08
    ä¸Ģå¼Ģå§ĭå°±
    -0.08
    POSITIVE LOGITS
    ango
    0.10
    æĦ«
    0.09
    ance
    0.09
    Backing
    0.09
    夫
    0.09
    ä¸įåħĭ
    0.09
    çļĦæĸĩåŃĹ
    0.08
    å¾Ĺ天
    0.08
    åij¨æģ©
    0.08
     Getty
    0.08
    Activations Density 0.157%

    No Known Activations