© 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. 35717
    Prev
    Next
    INDEX
    Explanations

    police

    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
    ä¹ı
    -0.11
    被æīĵ
    -0.09
    sWith
    -0.09
    åķĸ
    -0.08
    åĹĵ
    -0.08
    æµ·åĨĽ
    -0.08
    次ä¼ļè®®
    -0.08
    åī§ç»Ħ
    -0.08
    åĬŀåħ¬å®¤
    -0.08
    rics
    -0.08
    POSITIVE LOGITS
    çĤ·
    0.08
    ((&
    0.08
    à¸Ľà¸£à¸²
    0.08
    æł²
    0.08
    åºı
    0.08
     Bien
    0.08
    елÑĮ
    0.08
    lectron
    0.08
    说æĺ¯
    0.08
    erge
    0.08
    Activations Density 0.018%

    No Known Activations