© 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. 5519
    Prev
    Next
    INDEX
    Explanations

    nigeria election

    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
     Finished
    -0.09
    继ç»Ń
    -0.09
    ä¸įèĥ½åĨį
    -0.09
    acon
    -0.08
    вел
    -0.08
    èĥİ
    -0.08
    åķĨä¸ļåĮĸ
    -0.08
    enen
    -0.08
    antry
    -0.08
    à¤ł
    -0.08
    POSITIVE LOGITS
    ä¸Ģ度
    0.11
    åĩłæ¬¡
    0.10
    æĽ¾
    0.10
    _HEL
    0.10
    æľīä¸Ģ次
    0.09
    ä¹ŁæĽ¾
    0.09
    èµ·ä¼ı
    0.09
    osi
    0.09
     chees
    0.09
    æľĢåIJİä¸Ģ次
    0.09
    Activations Density 0.020%

    No Known Activations