© 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. 851
    Prev
    Next
    INDEX
    Explanations

    remove unwanted items

    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
    éĢĤåºĶ
    -0.10
    饥
    -0.09
    iske
    -0.09
    å°±æľīäºĨ
    -0.09
    åĩij
    -0.09
    æģ¤
    -0.09
    èµĹ
    -0.09
    .shtml
    -0.09
    åºĶ对
    -0.09
    Ñĩин
    -0.09
    POSITIVE LOGITS
    åİ»æİī
    0.18
    æİīäºĨ
    0.17
    æİī
    0.17
    åİ»éĻ¤
    0.17
     remove
    0.17
    没äºĨ
    0.17
    åıĸæ¶Ī
    0.16
    .remove
    0.15
    remove
    0.15
     removes
    0.15
    Activations Density 0.232%

    No Known Activations