© 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. 24278
    Prev
    Next
    INDEX
    Explanations

    email addresses and urls

    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
    è¨ĩ
    -0.10
    æģĭçĪ±
    -0.09
    anza
    -0.09
    èĹıçĿĢ
    -0.09
    åºķä¸ĭ
    -0.09
    ãģ¨ãģ£ãģ¦ãĤĤ
    -0.09
    ä¿®è¡Į
    -0.09
    éĩįéĩį
    -0.09
    è°ĥè¯ķ
    -0.09
    ä¿®çĤ¼
    -0.09
    POSITIVE LOGITS
     Rug
    0.09
    اب
    0.08
     GUIDE
    0.08
     Nicholson
    0.08
    .mas
    0.08
    è§Ħéģ¿
    0.08
    ÐŀС
    0.08
    PLAN
    0.08
    Envelope
    0.08
    amarin
    0.07
    Activations Density 0.001%

    No Known Activations