© 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. 26388
    Prev
    Next
    INDEX
    Explanations

    at best

    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
    akening
    -0.10
    eree
    -0.09
    nev
    -0.09
    atom
    -0.09
    Ñıв
    -0.08
    ATOM
    -0.08
    主æĦı
    -0.08
    owns
    -0.08
    quisite
    -0.08
    omorphic
    -0.08
    POSITIVE LOGITS
    ãĤ
    0.11
    ä¹Łåıªèĥ½
    0.10
    æľįåĬ¡äºİ
    0.10
    寥
    0.10
    æĭ¾
    0.10
    æľīåĩłä¸ª
    0.10
     Walton
    0.09
     glance
    0.09
    管çIJĨå·¥ä½ľ
    0.09
    è¦ģéĹ»
    0.09
    Activations Density 0.005%

    No Known Activations