© 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. 21085
    Prev
    Next
    INDEX
    Explanations

    stein-Barr virus or Canada

    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
    èĭ±æł¼
    -0.10
    çıĻ
    -0.09
    åĿļ
    -0.09
    åħ¬è¯ģ
    -0.09
    è¿Ļæīį
    -0.08
    å¹ķå¢Ļ
    -0.08
    mate
    -0.08
    åĸĢ
    -0.08
    éķ¿æ±Ł
    -0.08
    sing
    -0.08
    POSITIVE LOGITS
    渡
    0.10
    .lift
    0.10
    人家
    0.09
     ба
    0.09
    SPATH
    0.09
    SetColor
    0.09
    ä¸Ģæľ¬
    0.09
    ç©¿éĢı
    0.09
    èī²è°ĥ
    0.09
    æĩĭ
    0.09
    Activations Density 0.002%

    No Known Activations