© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21377
    Prev
    Next
    INDEX
    Explanations

    reporting services

    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
    æķħæĦı
    -0.10
    usan
    -0.10
    ä»ĬçĶŁ
    -0.10
    çĶŁçī©åѦ
    -0.09
    æĿ¡çº¦
    -0.09
    ä¼ī
    -0.09
    ressed
    -0.09
     ÙĪاÙĦÙĦÙĩ
    -0.09
    误ä¼ļ
    -0.09
    ê²½ìĺģ
    -0.09
    POSITIVE LOGITS
    å¸ĥé²ģ
    0.09
    å«ģ
    0.09
    YC
    0.09
    念
    0.09
    ä¸Ńè¶ħ
    0.09
     Fram
    0.08
    彪
    0.08
    éĬ®
    0.08
    Canon
    0.08
    å°ī
    0.08
    Activations Density 0.205%

    No Known Activations