© 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. 51976
    Prev
    Next
    INDEX
    Explanations

    DSL and DSM acronyms

    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
    ONGL
    -0.09
    èľ¡
    -0.09
    TING
    -0.09
    _visual
    -0.08
    stellen
    -0.08
     Lip
    -0.08
    SSIP
    -0.08
    ãģĵãģ¡ãĤī
    -0.08
    é¢Īéĥ¨
    -0.08
    csi
    -0.08
    POSITIVE LOGITS
    ogram
    0.10
    æĻ°
    0.09
    ADER
    0.09
    è®¤çľŁåŃ¦ä¹ł
    0.09
    å¸ļ
    0.09
    å®ĥåı¯ä»¥
    0.09
    olate
    0.09
    è¿Ļç§įæĸ¹å¼ı
    0.08
    Prov
    0.08
    äºĨä»ĸçļĦ
    0.08
    Activations Density 0.003%

    No Known Activations