© 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. 36868
    Prev
    Next
    INDEX
    Explanations

    subject or topic discussions

    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
    æŀ¢
    -0.10
    0
    -0.09
    åİ®
    -0.08
    åĪ¨
    -0.08
    åĽŀä¾Ĩ
    -0.08
    ãģ©
    -0.08
    æ¥Ķ
    -0.08
    å¤į
    -0.08
    çIJĨä¼ļ
    -0.08
    åĿļ强
    -0.08
    POSITIVE LOGITS
    è¯Ŀé¢ĺ
    0.22
     topics
    0.21
     topic
    0.21
    çļĦè¯Ŀé¢ĺ
    0.21
    -topic
    0.17
    topics
    0.17
     subjects
    0.17
     subject
    0.16
    topic
    0.16
    _topic
    0.16
    Activations Density 0.064%

    No Known Activations