© 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. 29743
    Prev
    Next
    INDEX
    Explanations

    turnovers and interceptions

    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
    伪
    -0.10
    bul
    -0.10
    çİ°å®ŀä¸Ń
    -0.09
    ä¸įåĩº
    -0.09
    çĪ·
    -0.09
    çŁ¥æĥħ
    -0.09
     Kidd
    -0.09
    ä»Ģä¹Īéĥ½
    -0.08
    å²Ĺ
    -0.08
    atch
    -0.08
    POSITIVE LOGITS
    èĻı
    0.09
    èĪĽ
    0.09
    å¼ķ
    0.09
     Eck
    0.09
    失误
    0.08
    é©Ń
    0.08
    è¤Ĵ
    0.08
    è¶Ĭå¤ļ
    0.08
    kek
    0.08
    å¼ķè¿Ľ
    0.08
    Activations Density 0.002%

    No Known Activations