© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36913
    Prev
    Next
    INDEX
    Explanations

    depending on the

    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
    aminer
    -0.10
    åİ»çľĭçľĭ
    -0.10
    ama
    -0.10
    åıªæĢķ
    -0.10
    åĶ¯ä¸ĢçļĦ
    -0.09
    ä¸ĢåįĬ
    -0.09
    çĤ¹äºĨ
    -0.09
    åŃ°
    -0.09
    æīįè¡Į
    -0.08
    ë¥ľ
    -0.08
    POSITIVE LOGITS
     Caught
    0.10
    çIJĽ
    0.09
    颤
    0.08
    à¹Ģย
    0.08
     Philly
    0.08
    åīįä¸ĸ
    0.08
    æĤ¨åIJĮæĦı
    0.08
    Caught
    0.08
    æ§İ
    0.08
    积
    0.08
    Activations Density 0.025%

    No Known Activations