© 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. 20800
    Prev
    Next
    INDEX
    Explanations

    forms of 'to be'

    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
    åħĢ
    -0.09
    æĶ¯æĴij
    -0.09
    ä¸Ģä¸ĭ
    -0.09
    æĥ³èµ·
    -0.09
    ä¸ĢæĬĬ
    -0.09
    ä¸Ģè½®
    -0.08
    ãĤªãĥ³
    -0.08
    .ProgressBar
    -0.08
    åħħåĪĨåıijæĮ¥
    -0.08
    izen
    -0.08
    POSITIVE LOGITS
    agar
    0.10
    ä¼ļåıijçĶŁ
    0.09
    utz
    0.09
    å¼Ģåıij建设
    0.09
    ishi
    0.09
    enz
    0.09
    à¸Īะ
    0.08
    agu
    0.08
     Asi
    0.08
    çĻ¼çĶŁ
    0.08
    Activations Density 0.085%

    No Known Activations