© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35115
    Prev
    Next
    INDEX
    Explanations

    live event on Saturday

    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
    æĪĺæĸĹ
    -0.09
    æ¢ħ西
    -0.09
    åľ°æĿ¿
    -0.09
    æĮ£æīİ
    -0.09
     dön
    -0.08
    ä»ģ
    -0.08
    åıĹ访
    -0.08
    Msp
    -0.08
     Manit
    -0.08
    Baseline
    -0.08
    POSITIVE LOGITS
    è£ħæī®
    0.09
    erus
    0.09
    ç¬ĭ
    0.09
    åѱ
    0.08
     Louis
    0.08
    çłĶ究
    0.08
    å¢ŀæ·»
    0.08
    ulia
    0.08
    é¾Ļ头
    0.08
    anan
    0.08
    Activations Density 0.056%

    No Known Activations