© 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. 9508
    Prev
    Next
    INDEX
    Explanations

    colors and descriptions

    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
    ationally
    -0.09
     bombs
    -0.09
    åľ¨æĦı
    -0.09
    æ»ļ
    -0.08
     Sunset
    -0.08
    ãģªãģĬ
    -0.08
    HEET
    -0.08
     sunset
    -0.08
    rites
    -0.08
    WA
    -0.08
    POSITIVE LOGITS
    çĶļ
    0.09
    ibase
    0.09
    Ø·ÙĪ
    0.09
    åľ°å¸¦
    0.09
    便ä¼ļ
    0.09
    便æĺ¯
    0.08
    æīĭæİĮ
    0.08
    æĶ¶èİ·
    0.08
    ç»Ħç»ĩé¢Ĩ导
    0.08
    озв
    0.08
    Activations Density 0.092%

    No Known Activations