© 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. 12209
    Prev
    Next
    INDEX
    Explanations

    highest, supreme, ideal, paramount

    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
    å±ģèĤ¡
    -0.11
    çĸ¾
    -0.11
    æŃ»è§Ĵ
    -0.09
    横
    -0.09
    é¢ĩ
    -0.09
    cen
    -0.08
    泸
    -0.08
    éĹ®éģĵ
    -0.08
    æĹĮ
    -0.08
    utta
    -0.08
    POSITIVE LOGITS
     Ñģобой
    0.10
    èİ«è¿ĩäºİ
    0.10
    ä¸įçĪ±
    0.09
    ä¸įåĩº
    0.09
    è²Ĥ
    0.09
    åĬŁå¾·
    0.09
    èĭŀ
    0.09
    èħĬ
    0.08
     Reached
    0.08
    çĻ½å¤©
    0.08
    Activations Density 0.062%

    No Known Activations