© 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. 21323
    Prev
    Next
    INDEX
    Explanations

    cognitive function and decline

    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
    æĭĹ
    -0.11
    紧迫
    -0.09
    ç¼Ĵ
    -0.09
    åĩ¹
    -0.08
    åĢĻ
    -0.08
    gars
    -0.08
    ç´§å¯Ĩ
    -0.08
    รา
    -0.08
    éķ³
    -0.08
    æĢĦ
    -0.08
    POSITIVE LOGITS
    èĦijåŃIJ
    0.23
    æĻºåķĨ
    0.20
    æĻºåĬĽ
    0.20
    头èĦij
    0.19
    Brains
    0.19
     brains
    0.18
     intellect
    0.17
    大èĦij
    0.17
    èĦijè¢ĭ
    0.17
    å¿ĥæĻº
    0.17
    Activations Density 0.202%

    No Known Activations