© 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. 12216
    Prev
    Next
    INDEX
    Explanations

    key presses and space bar

    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
     Wich
    -0.10
    ucid
    -0.09
    ocide
    -0.09
    æ²Ļ
    -0.09
    slider
    -0.08
    _lim
    -0.08
    åıĤè°ĭ
    -0.08
    èĺ¸
    -0.08
    并对
    -0.08
     Emblem
    -0.08
    POSITIVE LOGITS
    ç¼ij
    0.11
    è¿Ļå¥Ĺ
    0.11
    åѦåĪ°
    0.10
    zas
    0.09
    SetName
    0.09
    æµĩæ°´
    0.09
    èįŁ
    0.09
    ç»ĵ论
    0.09
    解éĶģ
    0.09
    åºĬä¸Ĭ
    0.09
    Activations Density 0.071%

    No Known Activations