© 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. 12225
    Prev
    Next
    INDEX
    Explanations

    manuscript or MS

    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
    quet
    -0.11
    çĩ®
    -0.10
    建çŃijå¸Ī
    -0.09
    Unhandled
    -0.09
    éĩįç»Ħ
    -0.09
    çĽ¥
    -0.09
    é½ģ
    -0.09
    çªģåıijäºĭ件
    -0.09
     Gat
    -0.08
    .Clock
    -0.08
    POSITIVE LOGITS
    æĬĦ
    0.11
    åĨĮ
    0.10
     manuscript
    0.09
    åŃĺéĩı
    0.09
    èĹı
    0.09
    MS
    0.09
    æ®ĭ
    0.09
    ç¢İçīĩ
    0.09
    å¾ģæ±Ĥ
    0.08
    .stub
    0.08
    Activations Density 0.050%

    No Known Activations