© 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. 3119
    Prev
    Next
    INDEX
    Explanations

    this

    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
    æ§
    -0.09
    è°İè¨Ģ
    -0.09
    åħ¶æīĢ
    -0.09
    tran
    -0.09
    mun
    -0.09
    è®°èĢħ表示
    -0.08
     ìĿ´ë¥¼
    -0.08
    éļıä¹ĭ
    -0.08
    å°±åľ¨äºİ
    -0.08
    gar
    -0.08
    POSITIVE LOGITS
    ữ
    0.09
    é³
    0.09
    æģ¤
    0.09
    erus
    0.08
    ulia
    0.08
    æĶ¾å¼Ģ
    0.08
    大äºĭ
    0.08
    FileDialog
    0.08
    SearchTree
    0.08
    缴åĪ°
    0.08
    Activations Density 0.060%

    No Known Activations