© 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. 40306
    Prev
    Next
    INDEX
    Explanations

    OLE application server controls

    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
    Negative Logits
    èĥĮçĿĢ
    -0.10
    æijĦåĥı头
    -0.09
     ascent
    -0.09
    ucs
    -0.09
    enen
    -0.09
    бил
    -0.09
    .sg
    -0.08
    _si
    -0.08
    éĺ´
    -0.08
    è¿ĻäºĽéĥ½æĺ¯
    -0.08
    POSITIVE LOGITS
    汶
    0.10
    第äºĮ次
    0.10
    åĨįçİ°
    0.09
    åĪĽå§ĭ
    0.09
    launcher
    0.09
     tie
    0.09
    çĶŁäº§ä¼ģä¸ļ
    0.08
    åĵģçīĮ形象
    0.08
    亥
    0.08
    çī©ä»¶
    0.08
    Activations Density 0.210%

    No Known Activations