© 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. 64018
    Prev
    Next
    INDEX
    Explanations

    monitoring and follow-up context

    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
    esc
    -0.09
    浪潮
    -0.08
     cedar
    -0.08
    éĢłè¡Ģ
    -0.08
    楷
    -0.08
    åıĶ
    -0.08
    å·¨æĺŁ
    -0.08
    é«»
    -0.08
    unger
    -0.08
    -css
    -0.08
    POSITIVE LOGITS
     suspected
    0.10
    æ¶īå«Į
    0.10
    .slim
    0.10
    æİ¢
    0.10
     suspects
    0.10
    åı¯çĸij
    0.09
    çĸijä¼¼
    0.09
     suspect
    0.09
    åĢĻéĢī
    0.09
    ç»Ĩå¾®
    0.09
    Activations Density 0.947%

    No Known Activations