© 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. 6290
    Prev
    Next
    INDEX
    Explanations

    list items

    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
    Negative Logits
    ç´¯äºĨ
    -0.10
    Îı
    -0.10
    çĶŁæ¶¯
    -0.09
    äºĽ
    -0.09
    ARAM
    -0.09
    åŁºç¡Ģä¸Ĭ
    -0.09
    è¿ĺ好
    -0.09
    个å¤ļ
    -0.09
    åĮĸçļĦ
    -0.09
    æģģ
    -0.09
    POSITIVE LOGITS
    Ñĩив
    0.09
    nels
    0.09
    _latency
    0.08
    ment
    0.08
    ersh
    0.08
    uttle
    0.08
    enschaft
    0.08
    iveness
    0.08
     gros
    0.08
    è´¡
    0.08
    Activations Density 0.151%

    No Known Activations