© 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. 12120
    Prev
    Next
    INDEX
    Explanations

    not followed by auxiliary verbs or 't

    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
     uninitialized
    -0.11
    åįģ足
    -0.10
     deb
    -0.10
    åįĪé¥Ń
    -0.09
    ä¸įçķĻ
    -0.09
    è¿Ļç§įæĥħåĨµ
    -0.09
    èİ·å¾ĹæĽ´å¤ļ
    -0.09
    çĶ»åĥı
    -0.09
    quate
    -0.09
    大家åı¯ä»¥
    -0.09
    POSITIVE LOGITS
    çĮ·
    0.10
    ials
    0.09
    é¦ĸåħĪæĺ¯
    0.09
    èĻŀ
    0.09
    ä¸Ģä¸Ģ
    0.09
    鸡
    0.09
    aris
    0.08
    ä¸Ģç¬Ķ
    0.08
    çĶļèĩ³æĺ¯
    0.08
    ones
    0.08
    Activations Density 0.025%

    No Known Activations