© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 922
    Prev
    Next
    INDEX
    Explanations

    show you how

    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
    getline
    -0.10
    缴éĶĢ
    -0.09
    éĩįç»Ħ
    -0.09
    å²³
    -0.09
    gear
    -0.08
    为äºĨæĽ´å¥½
    -0.08
    رÙĩ
    -0.08
    รà¸Ńà¸ĩ
    -0.08
    CIÃĵN
    -0.08
     даннÑĭÑħ
    -0.08
    POSITIVE LOGITS
    obl
    0.09
    åħ¥éŨ
    0.09
    åįĪ
    0.08
    ç®
    0.08
    ä¸ªé¡¹çĽ®
    0.08
    ãĥĹãĥªãĥ³
    0.08
    çŃīæĸ¹å¼ı
    0.08
    æīįæĺ¯çľŁæŃ£
    0.08
    èĢģ乡
    0.08
    åĬ¨äºº
    0.08
    Activations Density 0.020%

    No Known Activations