© 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. 3049
    Prev
    Next
    INDEX
    Explanations

    this followed by a noun

    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
    æŁ¥çľĭæĽ´å¤ļ
    -0.10
     ko
    -0.09
    å½¼
    -0.09
    天èĬ±æĿ¿
    -0.08
    个ä½ĵ
    -0.08
    寡
    -0.08
    人为
    -0.08
     Pemb
    -0.08
    åģ¶å°Ķ
    -0.08
    åĸĦäºİ
    -0.08
    POSITIVE LOGITS
    æŃ¤ä¸¾
    0.10
    asher
    0.10
    /***/
    0.10
    æī©
    0.09
    ffer
    0.09
    å¥ĸåѦéĩij
    0.08
    åļ
    0.08
    ä¼Ĭå§ĭ
    0.08
    fläche
    0.08
    è¡ĮæĶ¿æľºåħ³
    0.08
    Activations Density 0.064%

    No Known Activations