© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8782
    Prev
    Next
    INDEX
    Explanations

    academic performance and studies

    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
    è§ĦèĮĥåĮĸ
    -0.10
    社åĮº
    -0.10
    社åįĢ
    -0.09
    antro
    -0.09
    orris
    -0.09
    atal
    -0.09
    åѦéĻ¢
    -0.09
    éĶ¡
    -0.08
    otics
    -0.08
    åŃ
    -0.08
    POSITIVE LOGITS
    ä¸ĸçķĮåIJĦåĽ½
    0.09
    è°ĥæŁ¥æĺ¾ç¤º
    0.09
    åİĮ
    0.08
     survey
    0.08
    æµĭ
    0.08
    åħ¶ä»ĸåĽ½å®¶
    0.08
     Worldwide
    0.08
    male
    0.08
    _phy
    0.08
    å¼ºåĽ½
    0.08
    Activations Density 0.029%

    No Known Activations