© 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. 20874
    Prev
    Next
    INDEX
    Explanations

    Lyme disease or Wayne Martin

    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
    ä»İä¸ļ人åijĺ
    -0.09
    ización
    -0.09
    é£Ļ
    -0.09
    apr
    -0.09
    è¿ĻåĿĹ
    -0.08
    线索
    -0.08
    ä¸ĬéĻIJ
    -0.08
    éĵ©
    -0.08
    æŀģåĵģ
    -0.08
    æľªå©ļ
    -0.08
    POSITIVE LOGITS
    å¨ģ
    0.09
    å¤¸å¼ł
    0.09
    Bay
    0.09
    çĻ»
    0.08
    -indent
    0.08
    âĩ
    0.08
    èĸĩ
    0.08
    é«ĺè¡Ģåİĭ
    0.08
     Bay
    0.08
    indent
    0.08
    Activations Density 0.001%

    No Known Activations