© 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
    2. Qwen3-8B
    3. 18-RESID-BATCHTOPK-65K__L0-80
    4. 2595
    Prev
    Next
    INDEX
    Explanations

    Milwaukee and Wisconsin places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
     Iraqi
    -0.29
    æ²¹çͰ
    -0.28
     Saddam
    -0.28
     Coal
    -0.26
    ç¢Ľ
    -0.26
    éĩįåºĨå¸Ĥ
    -0.25
    èĿł
    -0.24
    åħŃåIJĪ
    -0.24
     Ches
    -0.24
     Malaysian
    -0.23
    POSITIVE LOGITS
     Milwaukee
    0.46
     Wisconsin
    0.43
    çijŀåħ¸
    0.35
     Finnish
    0.34
     Finland
    0.32
     Manit
    0.30
     Swedish
    0.29
    ä¿¡éĺ³
    0.29
    èĬ¬åħ°
    0.28
     WI
    0.28
    Activations Density 0.045%

    No Known Activations