© 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. 10126
    Prev
    Next
    INDEX
    Explanations

    legislative bodies and parliament

    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
    æĮŀ
    -0.09
    ikal
    -0.09
    ì¦Ī
    -0.09
    æĬ¥ä¸ļ
    -0.09
     Fine
    -0.09
    é¢Ħ订
    -0.09
    edin
    -0.09
    edio
    -0.08
    é«ĺæ°´å¹³
    -0.08
    é»İæĺİ
    -0.08
    POSITIVE LOGITS
    arians
    0.11
    .uk
    0.09
    ÙĨس
    0.09
    è¿Ļä¸įæĺ¯
    0.09
     haste
    0.09
    artner
    0.09
    çĵ¢
    0.09
    ively
    0.08
    帽
    0.08
    до
    0.08
    Activations Density 0.040%

    No Known Activations