© 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. 40413
    Prev
    Next
    INDEX
    Explanations

    board of directors

    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
    çŀ½
    -0.10
    çĤ¹æ»´
    -0.10
    æģį
    -0.09
    elig
    -0.09
    åľŁè±ª
    -0.09
    åĨĴ
    -0.09
    åĩºå¤Ħ
    -0.09
    íĿ¥
    -0.09
    廨
    -0.09
    ÑĥÑĤÑĮ
    -0.09
    POSITIVE LOGITS
     Uploaded
    0.09
     Conc
    0.08
     Resident
    0.08
    èij£äºĭä¼ļ
    0.08
    çĭ¬ç«ĭèij£äºĭ
    0.08
    æĬĽå¼ĥ
    0.08
     laz
    0.08
    3
    0.08
    æĸ°æµªå¾®åįļ
    0.08
     fatal
    0.08
    Activations Density 0.023%

    No Known Activations