© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 9360
    Prev
    Next
    INDEX
    Explanations

    actions or processes

    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
    åĪ©ç͍
    -0.10
    æĹ¨
    -0.09
    ummy
    -0.09
    Legacy
    -0.09
    ROID
    -0.09
     hete
    -0.08
    INGTON
    -0.08
    å°±è¿Ļæł·
    -0.08
    CONNECT
    -0.08
    çłĶ究表æĺİ
    -0.08
    POSITIVE LOGITS
    auge
    0.10
    æ¥Ķ
    0.09
    çīŁ
    0.09
    é̼
    0.09
    ä»İæĿ¥æ²¡
    0.09
    åĸĿ
    0.09
     purposes
    0.09
    å¼Ń
    0.08
    æĴ¬
    0.08
    åī¡
    0.08
    Activations Density 0.255%

    No Known Activations