© 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. 53222
    Prev
    Next
    INDEX
    Explanations

    Romanian, Romania, Moldova

    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
    åij¼åĴĮ
    -0.10
    èĥ¶åĽĬ
    -0.10
    åŁķ
    -0.10
    åİ»è¿ĩ
    -0.10
    åİĭ缩
    -0.09
    çĪ·
    -0.09
    tron
    -0.09
    heimer
    -0.09
    åIJĦç§įåIJĦæł·
    -0.09
    DIR
    -0.09
    POSITIVE LOGITS
     Romanian
    0.14
     Romania
    0.13
    Äĥ
    0.10
     Dresden
    0.10
     zb
    0.09
    inea
    0.09
     Mate
    0.09
    Roman
    0.09
     Cypress
    0.09
    ained
    0.09
    Activations Density 0.072%

    No Known Activations