© 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. 8574
    Prev
    Next
    INDEX
    Explanations

    first appearance of evidence

    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
     Announcement
    -0.09
    大éĻĨ
    -0.09
     اÙĦأج
    -0.09
    uder
    -0.09
     Theodore
    -0.09
    à¸ģำ
    -0.09
    лав
    -0.08
    COPE
    -0.08
    åį¿
    -0.08
    ä¼ļä¸Ĭ
    -0.08
    POSITIVE LOGITS
    è®°è½½
    0.15
    åı²æĸĻ
    0.13
    èµĦæĸĻæĺ¾ç¤º
    0.12
    è¿Ļ段
    0.11
    è®°å½ķ
    0.11
    书记
    0.11
    è¨ĺ
    0.11
    åİĨåı²
    0.10
    äºĭ迹
    0.10
     اÙĦتارÙĬØ®
    0.10
    Activations Density 0.154%

    No Known Activations