© 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. 51583
    Prev
    Next
    INDEX
    Explanations

    to + verb

    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
    زÙĬ
    -0.09
    ÑĢов
    -0.08
    ifen
    -0.08
    éĮ¾
    -0.08
    éĥ½å¸Ĥ
    -0.08
    agraph
    -0.08
    éĤ£æł·çļĦ
    -0.08
    è¾¹éĻħ
    -0.08
    嫦
    -0.08
    å¼ķ
    -0.08
    POSITIVE LOGITS
    å°±åľ¨äºİ
    0.10
    ler
    0.10
    以åıĬåħ¶ä»ĸ
    0.09
    vero
    0.09
    æĬĺèħ¾
    0.09
    cer
    0.09
    æĮļ
    0.09
    å¯ħ
    0.09
    ernel
    0.09
    çħ§æĸĻ
    0.09
    Activations Density 0.103%

    No Known Activations