© 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. 62839
    Prev
    Next
    INDEX
    Explanations

    Michigan court and legal terms

    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
    京åŁİ
    -0.10
    åľ¨å¹¿å·ŀ
    -0.10
    çģ¸
    -0.10
    åľ¨äº¬
    -0.10
    æĤīå°¼
    -0.09
    èĻ±
    -0.09
    zion
    -0.09
    澳洲
    -0.09
    æ¾³
    -0.09
    西æ¹ĸ
    -0.09
    POSITIVE LOGITS
     Michigan
    0.15
    Michigan
    0.14
     Detroit
    0.14
    Detroit
    0.13
     Wolverine
    0.13
     Illinois
    0.12
     Wisconsin
    0.11
    éŀįå±±
    0.11
     Manit
    0.11
    大åºĨ
    0.10
    Activations Density 0.444%

    No Known Activations