© 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. 24215
    Prev
    Next
    INDEX
    Explanations

    iconic, famous, recognized things

    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
    _minor
    -0.10
    廪
    -0.10
    èĬ±å¼Ģ
    -0.09
    å°ıä¼Ļ
    -0.09
    åĪ°åľº
    -0.09
    ä¸įå¼Ģ
    -0.09
    åĬŀ
    -0.09
    çĶ»çĶ»
    -0.09
    æĽ´æľī
    -0.09
    æĿŀ
    -0.09
    POSITIVE LOGITS
    æ·±åħ¥äººå¿ĥ
    0.15
     iconic
    0.14
    家åĸ»æĪ·æĻĵ
    0.13
    ç»ıåħ¸
    0.12
    符åı·
    0.12
    ç»ıåħ¸çļĦ
    0.12
    åįĥåı¤
    0.12
    çŁ¥åIJį度
    0.11
     famously
    0.11
    symbols
    0.11
    Activations Density 0.327%

    No Known Activations