© 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. 40108
    Prev
    Next
    INDEX
    Explanations

    comments in code

    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
    Not in Any Lists

    No Comments

    Negative Logits
     kå
    -0.09
    æĬĬæı¡
    -0.09
    æķ´å½¢
    -0.09
    phony
    -0.08
    éĢŃ
    -0.08
    ocab
    -0.08
    umeric
    -0.08
    ç»Łæ²»
    -0.08
    éļĶå£ģ
    -0.08
     اÙĦسÙĬ
    -0.08
    POSITIVE LOGITS
    麾
    0.10
     Fraser
    0.08
    äºĭ實
    0.08
     treÅĽci
    0.08
    åµĺ
    0.08
    è²ĵ
    0.08
    amen
    0.07
    åŁ¤
    0.07
    idad
    0.07
    azard
    0.07
    Activations Density 0.054%

    No Known Activations