© 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. 39089
    Prev
    Next
    INDEX
    Explanations

    gluconeogenesis

    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
    ä¿¡å¿ĥ
    -0.11
    羣è¯ļ
    -0.10
    çĭŃ
    -0.10
    é¦ĸè½®
    -0.10
    å§Ĭ
    -0.10
    æ¶ī
    -0.09
    .setColumns
    -0.09
     Peb
    -0.09
    éªĪ
    -0.09
    mlink
    -0.09
    POSITIVE LOGITS
    éĬ®
    0.09
    åħ¥æĪ·
    0.09
     Sense
    0.09
    zen
    0.08
    å±ı
    0.08
    å±ģèĤ¡
    0.08
    åįİ缼
    0.08
    Sense
    0.08
    going
    0.08
    éŨæĪ·ç½ijç«Ļ
    0.08
    Activations Density 0.088%

    No Known Activations