© 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. 12441
    Prev
    Next
    INDEX
    Explanations

    experienced professionals and roles

    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
    çĮ©
    -0.08
    æĺĶæĹ¥
    -0.08
    å¥ĸéĩij
    -0.08
     ÑģлÑĥÑĩаÑı
    -0.08
    第ä¸ĢåIJį
    -0.08
    éĻĮçĶŁäºº
    -0.08
    槿
    -0.08
    æĸ°æĹ¶æľŁ
    -0.08
     chance
    -0.07
    osi
    -0.07
    POSITIVE LOGITS
    iate
    0.11
     جدا
    0.11
    人éĥ½
    0.10
     enough
    0.10
    iated
    0.10
    åģļæ³ķ
    0.10
     Wich
    0.10
    yı
    0.09
    gers
    0.09
    iments
    0.09
    Activations Density 0.011%

    No Known Activations