© 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. 35388
    Prev
    Next
    INDEX
    Explanations

    trailing or behind

    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
    åĿĬ
    -0.10
    omon
    -0.10
    æ´½
    -0.09
    æħ·æħ¨
    -0.09
    模仿
    -0.09
    ieÅĦ
    -0.09
    AtA
    -0.09
    ä»Ģä¹Ī
    -0.09
    æľīä¸Ģå®ļçļĦ
    -0.08
    éªĨ
    -0.08
    POSITIVE LOGITS
    åĬ£åĬ¿
    0.10
    èIJ½åIJİ
    0.08
    -turned
    0.08
    endo
    0.08
    çªĺ
    0.08
    tons
    0.08
     ëı
    0.08
    нак
    0.08
    æĽĮ
    0.08
    æĹ¥æĬ¥éģĵ
    0.08
    Activations Density 0.010%

    No Known Activations