© 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. 64104
    Prev
    Next
    INDEX
    Explanations

    real life, reality, real world

    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
    éĥİ
    -0.11
    çħ§æĸĻ
    -0.11
    á´
    -0.09
    æľĿ
    -0.09
    å¤ĸåĽ½
    -0.09
    åľ¨æĹ¥æľ¬
    -0.08
    åѤçĭ¬
    -0.08
    око
    -0.08
    atic
    -0.08
    åıij表äºĨ
    -0.08
    POSITIVE LOGITS
    çİ°å®ŀ
    0.26
    çİ°å®ŀä¸Ń
    0.22
    çİ°å®ŀçĶŁæ´»
    0.22
    çı¾å¯¦
    0.19
     reality
    0.19
     real
    0.17
    real
    0.16
    REAL
    0.16
    (real
    0.15
     Reality
    0.15
    Activations Density 0.065%

    No Known Activations