© 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. 18484
    Prev
    Next
    INDEX
    Explanations

    Romanian

    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
    æŀķ
    -0.10
    ä¸įä¸Ĭ
    -0.10
    èī¨
    -0.10
    å¾Ĺ天
    -0.09
    à¹Ĥà¸Ľà¸£à¹ģ
    -0.09
    ocado
    -0.09
    ðŁ¦Ĭ
    -0.08
    몽
    -0.08
    .mvc
    -0.08
    -console
    -0.08
    POSITIVE LOGITS
     Romanian
    0.12
     Romania
    0.11
    Äĥ
    0.10
    ä¹ħ
    0.08
     Roma
    0.08
     din
    0.08
    ului
    0.08
     Mold
    0.08
    æĮ¤
    0.08
    Roman
    0.08
    Activations Density 0.069%

    No Known Activations